Autonomous Mobile Localization Using Adaptive Environment Maps

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing autonomous mobile apparatuses face challenges in robustly estimating their location in environments with changing lighting conditions, especially when clear landmarks are absent, leading to unstable operation.

Innovation Solution

The apparatus employs a wide-angle lens imager for capturing images of the ceiling light and surrounding environment, using feedback signals from a charger and odometry to perform monocular SLAM, and selects an appropriate environment map based on lighting and brightness information for robust location estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a landmark-based approach is used for location estimation, then robustness against environmental changes is improved, but operational stability in environments without clear landmarks deteriorates

Engineering Contradiction:

Improverobustness of location estimationVSAvoidoperational stability

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system changes the parameter of landmark selection by considering multiple candidates with varying degrees of environmental invariance rather than selecting a single fixed type of landmark. This allows adaptation to different environmental conditions where clear landmarks may or may not be present.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The landmark selection becomes dynamic rather than static. The system continuously evaluates and selects from multiple landmark candidates based on current environmental conditions, allowing the apparatus to adapt between environments with and without clear landmarks.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If environment maps are created using camera images, then location estimation capability is improved, but accuracy under varying lighting conditions deteriorates

Engineering Contradiction:

Improvelocation estimation accuracyVSAvoidlighting condition sensitivity

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system extracts multiple candidate landmarks with different characteristics from the environment map, separating those that are invariant to lighting changes from those that are not. This allows selection of appropriate landmarks based on current lighting conditions.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary evaluation of multiple landmark candidates during map creation, pre-categorizing them by their environmental invariance characteristics. This prepares the system to quickly select appropriate landmarks when location estimation is needed under varying conditions.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentEP3537249B1Autonomous mobile apparatus, autonomous move method, and program

Publication Date: 2023.03.01 CASIO COMPUTER CO LTD

Figure 1~2
Figure 3
Figure 4

AI summary

An improved technique that enables robust estimation of a location of an autonomous mobile apparatus (100) over environment change is provided. The autonomous mobile apparatus (100) comprises a controller (10) and a memory (20). The controller (10) is configured to acquire environment information that is information of a surrounding environment of the autonomous mobile apparatus (100), based on the acquired environment information, select, as an estimation environment map, an environment map that is suitable for the surrounding environment from among environment maps that are saved in the memory (20), and estimate a location of the autonomous mobile apparatus (100) using the selected estimation environment map and an image of surroundings of the autonomous mobile apparatus (100) that is captured by an imager (33).