Using Machine Learning to Create High-Efficiency Optical Design Tools

Technology #ua19-048

Questions about this technology? Ask a Technology Manager

Download Printable PDF

Categories
Researchers
Rongguang Liang
Professor, Optical Sciences
Caleb Gannon
PhD Student, Optical Sciences
Managed By
Amy Phillips
Sr. Licensing Manager (520) 621-9579

Title:  Using Machine Learning to Create High-Efficiency Optical Design Tools

 

Invention:  Researchers at the University of Arizona have developed systems and techniques that enable a determination of an estimated mapping from the design parameter space to the performance parameter space in real time.

 

Background:  Optical lens design is the process of designing a lens to meet a set of performance requirements and constraints.  The design process is computationally intensive.  One problem in optical system design is that, although finding a mapping from the design parameter space to the performance parameter space is easy (taking only a single ray trace), given a desired set of performance characteristics, it is extremely complicated to determine the corresponding design parameters.

 

Advantages:

* saves time

* increases functionality of design software

 

Applications:

* optical design software

 

Contact:  Amy Phillips

amyp@tla.arizona.edu

Refer to case number UA19-048