Visual Servo Feature Matching for Markerless Robot Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-based visual servo systems struggle to extract graphical features from target objects lacking detectable markers or distinctive shapes, leading to inaccurate feedback signals and potential erroneous control.
Innovation Solution
A control method that extracts goal feature points from a goal image, performs matching with candidate feature points from a current image, and generates a control signal using matching information to stabilize visual servo operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image-based visual servo is used to reduce computational load and improve control precision, then control precision is improved, but reliability deteriorates when graphical features cannot be extracted from the target object
Solution Approach 1:
The patent applies preliminary action by extracting and storing goal feature points from the goal image before the visual servo operation begins. This pre-extraction ensures that reference feature points are available even when the target object lacks distinctive graphical features during operation, thereby maintaining control precision and reliability
Solution Approach 2:
The patent uses goal feature points as an intermediary element that mediates between the image-based visual servo system and the target object. By matching current feature points against pre-extracted goal feature points, the system can reliably control the movable portion even when direct feature extraction from the target object fails
2Adaptability or versatility
If feature point extraction is performed from current image to enable visual servo control, then adaptability is improved, but measurement precision deteriorates when the target object lacks distinctive features
Solution Approach 1:
The system performs preliminary extraction of goal feature points from the goal image before operation. This allows the system to adapt to various target objects without requiring them to have distinctive graphical features, while maintaining measurement precision by comparing against pre-extracted reference points
Solution Approach 2:
The patent creates a copy of the goal feature points from the goal image and uses this copied reference data for matching during operation. This copying approach enables the system to adapt to different objects while maintaining precise measurement by referencing the copied goal features rather than relying on features from the current target object
Data Source
AI summary
A control method for controlling an apparatus including a movable portion by a visual servo includes obtaining a goal image corresponding to a goal positional relationship between the movable portion and a target object, extracting goal feature points whose information has a degree of freedom of ψ from the goal image by image processing, obtaining a current image corresponding to a current positional relationship between the movable portion and the target object, extracting candidate feature points from the current image by image processing, extracting current feature points associated with the goal feature points from the candidate feature points by performing matching processing between the candidate feature points and the goal feature points, and generating, by using matching information based on matching between the current feature points and the goal feature points in the matching processing, a control signal for moving the movable portion at a degree of freedom of n.