System and method for machine-learning-enabled micro-object density distribution control with the aid of a digital computer
US11921488B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 15, 2020 |
| Grant date | Mar 5, 2024 |
| Priority date | — |
| Expiry date | May 12, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG05B2219/41345
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
System and method that to shape micro-object density distribution (how densely the micro-objects are assembled in particular spatial regions) are provided. A high speed camera tracks existing object density distribution. An array of photo-transistor-controlled electrodes is used to generate a dynamic potential energy landscape for manipulating objects with both DEP and EP forces, and a video projector is used actuate the array. One or more computing devices are used to: process images captured by the camera to estimate existing density distribution of objects; receive a desired density distribution of micro-objects; define a model describing a variation of micro-object density over time due to capacitance-based interactions; generate a sequence of electrode potential that when generated would minimize error between the existing density distribution and a desired density distribution; and use the sequences of electrode potentials to actuate the electrodes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.