Drone Path Control Using Keyframe-Based Indoor Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Drones face challenges in maintaining accurate positioning and following a predefined path indoors where GPS signals are unavailable, leading to error accumulation in SLAM-based navigation.
Innovation Solution
A mobile body control device and method that utilize a keyframe database to associate image features with predefined positions and attitudes, enabling accurate navigation by verifying captured images against registered keyframes and controlling movement based on calculated positions and attitudes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If SLAM processing is used for self position estimation, then autonomous flight capability is improved, but error accumulation occurs leading to deviation from predefined path
Solution Approach 1:
The system continuously captures images during flight, compares them with pre-registered keyframes, and uses the matching results to calculate current position and attitude. This feedback mechanism corrects SLAM estimation errors by providing periodic absolute position references, maintaining accurate path following throughout the flight.
Solution Approach 2:
Before flight, the system performs preliminary action by capturing images of the movement space and registering keyframes with their corresponding positions and attitudes in a database. This pre-prepared reference data enables accurate position calculation during autonomous flight without requiring real-time external GPS signals.
2Measurement precision
If GPS position information is used to correct SLAM errors, then self position accuracy is improved, but the system cannot operate indoors where GPS signals are unavailable
Solution Approach 1:
The system creates a copy of the movement space environment by capturing images and registering keyframes with their position and attitude information in a database before flight. This virtual map serves as a reference for position estimation indoors, replacing the need for GPS signals and enabling autonomous navigation in GPS-denied environments.
3Measurement precision
If image feature verification against registered keyframes is performed, then position calculation accuracy is improved, but processing time and computational load increase
Solution Approach 1:
Instead of comparing the current image with all registered keyframes, the system performs partial action by comparing only with the nearest neighboring keyframe in terms of time or spatial position. This selective comparison maintains position calculation accuracy while significantly reducing processing time and computational load during autonomous flight.
Data Source
AI summary
Provided are a device and method which realize movement according to a predefined path even when absolute position information from the exterior, such as a GPS signal, cannot be input. Using a keyframe database that associates, and registers, a feature of a keyframe selected from images shot by a camera of a movement space for a mobile body such as a drone and a position and attitude of the keyframe in a coordinate system defining the movement space, verifies a feature of an image captured by a camera of the mobile body is verified against a keyframe feature. The position and attitude of the mobile body are then calculated on the basis of the position and attitude of the keyframe in the coordinate system defining the movement space, registered in the database in association with the keyframe for which the verification is successful. Then, the movement of the mobile body is controlled on the basis of the position and attitude calculated.