Image-Based AGV Route Control Using Camera Orientation Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous moving apparatuses, such as AGVs, can deviate significantly from their intended routes due to errors in position estimation, leading to potential collisions.
Innovation Solution
An information processing apparatus that extracts and compares images from different cameras to estimate the orientation of each camera, allowing for precise control of the moving apparatus based on these orientations to prevent collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the autonomous moving apparatus uses position estimation based on odometry and SLAM method, then the apparatus can perform own position estimation without external infrastructure, but the position estimation error accumulates and causes large deviation from the defined route
Solution Approach 1:
The patent introduces a camera as an intermediary device to capture images of the environment. By comparing captured images with pre-stored map images, the system obtains intermediary position information that helps correct the accumulated odometry and SLAM errors, thereby improving position estimation accuracy without requiring external infrastructure.
Solution Approach 2:
The system implements a feedback mechanism where the estimated position from odometry and SLAM is continuously compared with position information derived from image matching. When the deviation exceeds a threshold, the system corrects the position estimate using the image-based position information, creating a closed-loop feedback system that prevents error accumulation.
2Measurement precision
If the apparatus corrects position by traveling largely off the defined route when deviation exceeds error range, then the position estimation error is corrected, but the apparatus may cause collision or accident with other objects
Solution Approach 1:
The system performs preliminary action by continuously capturing images and comparing them with map images in advance. This allows the system to detect position deviations early and make gradual corrections along the route, rather than making large sudden deviations that could cause collisions. The correction is performed step-by-step by adjusting the route based on image matching results.
3Measurement precision
If the apparatus uses multiple photographed images for creating three-dimensional image, then the position estimation accuracy is improved, but the processing time and computational load increase
Solution Approach 1:
The system extracts only the necessary features and information from the captured images for position estimation. By using image matching algorithms that compare key features between captured images and map images, the system avoids processing the entire image data, thereby reducing computational load and processing time while maintaining position estimation accuracy.
Data Source
AI summary
The information processing apparatus includes an extraction unit configured to extract at least one first photographed image, the first photographed image being similar to a second photographed image which is photographed by using a second photographing apparatus mounted on a moving apparatus, the moving apparatus being moving in a predetermined region, from a plurality of first photographed images which are photographed by using a first photographing apparatus for creating a three-dimensional image of the predetermined region, an estimation unit configured to estimate a first photographing orientation of the first photographing apparatus, the first photographing apparatus photographing the first photographed image which is extracted, and a second photographing orientation of the second photographing apparatus at a time when the second photographed image is photographed, and a control unit configured to control an action of the moving apparatus based on the first photographing orientation and the second photographing orientation.