Vision Alignment Through Occlusion Using Secondary Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In manufacturing processes, aligning two flat work pieces where one partially occludes the critical alignment features of the other is challenging, as the occlusion hinders the camera's view and illumination, making precise alignment difficult.
Innovation Solution
A vision system learns secondary alignment features to guide the motion of a manipulator and motion stage, exposing primary alignment features and establishing their relationship to ensure accurate alignment, using deterministic movements to achieve proper positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the first work piece is moved into position over the second work piece for alignment, then the assembly process can proceed, but the first work piece occludes the critical alignment features of the second work piece from the camera's view
Solution Approach 1:
The patent introduces a transparent or translucent intermediary layer (adhesive layer) between the first and second work pieces. This intermediary allows optical penetration so the camera can see through the first work piece to detect alignment features on the second work piece, while still maintaining the physical assembly structure. The adhesive layer acts as an optical mediator that doesn't block the vision system.
Solution Approach 2:
The patent utilizes optical property changes by selecting materials with specific transparency characteristics. The adhesive layer is chosen to be transparent or translucent at the operating wavelength, allowing light to pass through the first work piece and illuminate the alignment features on the second work piece, enabling vision-based detection despite the overlying structure.
2Ease of operation
If the first work piece hovers above the second work piece during manipulation, then positioning and alignment can be performed, but the occlusion prevents accurate measurement of the gap between edges
Solution Approach 1:
The transparent adhesive layer serves as an optical window that allows the vision system to see through the first work piece to measure the gap between edges of both work pieces. This intermediary enables the camera to capture alignment feature positions and calculate gap dimensions even when the work pieces are in the hovering manipulation phase.
Solution Approach 2:
The patent extends the measurement capability from surface-level features to three-dimensional gap measurement by using the transparent adhesive layer as an optical pathway. The vision system can now measure not only in-plane positions but also the vertical gap dimension between the hovering first work piece and the second work piece below.
3Reliability
If the first work piece is lowered into engagement with the second work piece, then final assembly is achieved, but the occlusion of alignment features persists throughout the process
Solution Approach 1:
The transparent adhesive layer maintains optical transparency throughout the entire assembly process, from hovering to final engagement. This consistent intermediary allows the vision system to continuously track alignment features and monitor the alignment process without information loss, regardless of the relative positions or contact state of the work pieces.
Solution Approach 2:
The patent enables continuous vision-based alignment monitoring throughout the entire manipulation and assembly process. The transparent adhesive layer ensures unbroken optical access to alignment features, allowing the vision system to continuously provide feedback for adjusting positions and maintaining alignment accuracy from the initial hovering state through final engagement.
Data Source
AI summary
This invention provides a system and method for aligning a first work piece with an underlying second work piece in the presence of occlusion by the first work piece of critical alignment features of the second work piece. The vision system, which guides the motion of a manipulator holding the first work piece and a motion stage holding the second work piece, learns secondary alignment features at least one of the first and second work pieces. Using these secondary features, the vision system determines alignment between the work pieces and guides the manipulator and the motion stage to achieve alignment as the first work piece engages the second work piece. The secondary features are used to define a course alignment. Deterministic movements of the manipulator and/or motion stage are used to learn the relationship between the secondary and primary features. Secondary features are used to direct alignment.