Warehouse Vehicle Localization Using Ceiling Light Point Fixes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Industrial vehicles navigating through warehouses face challenges in localization and navigation due to the lack of effective features extracted from ceiling lights, particularly in environments with varying lighting configurations and sparse feature sets.

Innovation Solution

An industrial vehicle equipped with a camera and processors that capture images of ceiling lights, extract raw feature components, classify them, filter out unusable features, and determine centerlines and point fixes to navigate accurately using machine-readable instructions, employing techniques like Hough transforms and convex hull algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional localization methods are used in warehouses with varying lighting configurations, then navigation reliability deteriorates, but switching to ceiling light-based localization increases measurement precision

Engineering Contradiction:
Improvelocalization accuracyVSAvoidnavigation reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent segments the ceiling light features into multiple components including centerlines, corners, and individual light fixtures. By dividing the localization task into extracting these discrete geometric features from ceiling lights, the system achieves precise localization coordinates while maintaining reliability across varying lighting configurations through multiple feature types

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a universal localization system that works across different warehouse environments with varying lighting configurations. The ceiling light feature extraction methodology is adaptable to different ceiling light types and arrangements, making the localization system universally applicable while maintaining both precision and reliability

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

2Measurement precision

If complex feature extraction from ceiling lights is implemented, then navigation accuracy improves, but device complexity increases

Engineering Contradiction:
Improvenavigation accuracyVSAvoidfeature extraction complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts specific geometric features (centerlines, corners) from ceiling lights by isolating them from the overall image. This extraction approach achieves high navigation accuracy by focusing on key geometric properties while keeping the processing complexity manageable through targeted feature selection rather than comprehensive analysis

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary classification of ceiling light features before detailed extraction. By pre-identifying and categorizing ceiling light structures in the image, the system prepares the data in advance, which simplifies subsequent extraction operations and reduces overall computational complexity while maintaining accuracy

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If comprehensive ceiling light feature extraction is performed, then localization precision improves, but processing time increases

Engineering Contradiction:
Improvelocalization precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential geometric features (centerlines and corners) from ceiling lights that are necessary for localization, rather than processing all possible image features. This selective extraction maintains high localization precision while significantly reducing processing time by focusing computational resources on critical features only

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3751515B1Industrial vehicles with point fix based localization
Publication Date: 2023.10.25 CROWN EQUIP CORP
  • EP3751515B1 patent drawingFigure 1
  • EP3751515B1 patent drawingFigure 2
  • EP3751515B1 patent drawingFigure 3

AI summary

According to the embodiments described herein, an industrial vehicle can include a camera and one or more processors. The camera can capture an input image of ceiling lights of the ceiling of the warehouse. The one or more processors can execute machine readable instructions to determine a centreline from a from of ceiling lights in the input image by extracting raw feature components and separating them into different classes of ceiling lights. The machine readable instructions executed by the one or more processors can determine ceiling light corners by selecting a usable portion of the ceiling lights, extracting ceiling light features from the extracted raw feature components in the usable portion of the ceiling lights. The machine readable instructions executed by the one or more processors can further select a set of point fixes from the ceiling light corners and navigate the industrial vehicle through the warehouse utilizing the centerline and the set of point fixes.