Training, testing, and verifying autonomous machines using simulated environments
US-2019303759-A1 · Oct 3, 2019 · US
US11280905B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11280905-B2 |
| Application number | US-202016859306-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 27, 2020 |
| Priority date | May 3, 2019 |
| Publication date | Mar 22, 2022 |
| Grant date | Mar 22, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method of stereoscopic mapping an underwater location includes determining a relative position and relative distance between two separate sensors on separate underwater platforms. Each of the two separate sensors scans a same underwater feature from its respective determined relative position. A stereoscopic image of the underwater feature is created from the two scanned images.
Opening claim text (preview).
What is claimed is: 1. A method of stereoscopic mapping an underwater location, comprising: determining a relative position and relative distance between two separate sensors on two separate underwater platforms; scanning with the two separate sensors a same underwater feature from the two determined relative positions; and creating a stereoscopic image of the underwater feature from the two scanned images. 2. The method of claim 1 , wherein scanning with sensors comprises scanning with sonar to generate sonar images. 3. The method of claim 1 , wherein processing sonar images is accomplished using a graphics processor on one of the two underwater platforms. 4. The method of claim 3 , wherein graphics processing on one of the at least two underwater platforms is performed at a first resolution. 5. The method of claim 4 , and further comprising additional graphics processing, wherein additional graphics processing is at a second resolution higher than the first resolution. 6. The method of claim 1 , wherein processing sonar images is accomplished using a graphics processor on an external platform to the two underwater platforms. 7. A method of mapping an underwater environment, comprising: establishing communication between at least two underwater platforms, each underwater platform having a sonar system; determining a distance between the at least two underwater platforms; propagating sonar waves from the sonar system of each of the at least two underwater platforms to image a feature in the underwater environment; and processing sonar images from each of the at least two underwater platform sonar systems with a graphics processor to generate a stereoscopic image of the underwater feature. 8. The method of claim 7 , wherein processing sonar images is accomplished using a graphics processor on a one of the at least two underwater platforms. 9. The method of claim 8 , wherein graphics processing on a one of the at least two underwater platforms is performed at a first resolution. 10. The method of claim 9 , and further comprising additional graphics processing, wherein additional graphics processing is at a second resolution higher than the first resolution. 11. The method of claim 9 , and further comprising improving resolution using averaging and convergent mathematical solutions. 12. The method of claim 7 , wherein processing sonar images is accomplished using a graphics processor on an external platform to the at least two underwater platforms. 13. The method of claim 7 , wherein images are taken at different frequencies. 14. The method of claim 13 , wherein images are taken at frequencies ranging from about 2 kilohertz to about 15 kilohertz. 15. The method of claim 7 , wherein images are stitched together using identifiable overlapping features of the underwater feature. 16. An underwater platform, comprising: a platform body with a propulsion system, a communication system, an internal navigation system, and a computer control for directing platform operation; and a sonar system; wherein the computer control is configured to: establish communication between the platform and another separate underwater platform; determine a distance between the two underwater platforms; propagate sonar waves from the sonar system to image a feature in the underwater environment; and direct processing of sonar images from each of the at least two underwater platforms with a graphics processor to generate a stereoscopic image of the underwater feature. 17. The platform of claim 16 , wherein the computer control is further configured to process sonar images using a graphics processor on a one of the at least two underwater platforms. 18. The platform of claim 17 , wherein the computer control is further configured to process graphics on a one of the at least two underwater platforms at a first resolution. 19. The platform of claim 18 , the computer control is further configured to control stitching together of multiple sonar images using identifiable overlapping features of the underwater feature. 20. The platform of claim 16 , wherein the platform is an autonomous underwater vehicle.
Processing image signals (for multi-view video sequence encoding H04N19/597) · CPC title
with receivers spaced apart · CPC title
for mapping or imaging · CPC title
using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) · CPC title
autonomously operating · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.