Self-Position Estimation Accuracy Notification for Mobile Robots

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for self-position estimation in robots and movable apparatuses, such as AGVs, face challenges in accurately determining the factors that affect the accuracy of self-position estimation, making it difficult to maintain stable movement control.

Innovation Solution

An information processing device is developed with a self-position estimating unit, an accuracy determining unit, and a notification unit that uses image analysis to detect objects and notify users when accuracy falls below a predetermined range, allowing for improved self-position estimation by combining image and sensor information, and reducing unnecessary calculations to conserve resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If self-position estimation is performed using image information, then movement control stability is improved, but the ability to determine accuracy factors deteriorates

Engineering Contradiction:
Improvemovement control stabilityVSAvoidself-position estimation accuracy determination
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The system segments the self-position estimation process into multiple independent analysis components: feature amount extraction, object detection, and accuracy determination. Each segment analyzes specific aspects of the image data separately, allowing the system to identify which specific factor (feature amount or object detection result) is causing accuracy degradation, thereby resolving the contradiction between maintaining stability and determining accuracy factors.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If image analysis is performed to detect objects, then accuracy determination is improved, but computational resources are consumed

Engineering Contradiction:
Improveself-position estimation accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs partial image analysis by selectively executing object detection only when necessary for accuracy determination. Instead of continuously performing full image analysis, the system analyzes specific portions of the image data based on the current estimation accuracy requirements, reducing unnecessary computational resource consumption while maintaining adequate accuracy determination capability.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20240177342A1Information processing device, information processing method, and storage medium
Publication Date: 2024.05.30 CANON KK
  • US20240177342A1 patent drawing
  • US20240177342A1 patent drawing
  • US20240177342A1 patent drawing

AI summary

An information processing device that can notify of information on an object affecting accuracy in self-position estimation includes: a self-position estimating unit configured to estimate a self-position on the basis of an image; an accuracy determining unit configured to determine accuracy in estimation of the self-position; an image analyzing unit configured to detect an object from the image; and a notification unit configured to notify of information on the object detected by the image analyzing unit in a case in which the accuracy is outside of a predetermined range.