公开(公告)号：US20230169764A1

公开(公告)日：2023-06-01

申请号：US17540037

申请日：2021-12-01

Applicant: X Development LLC

Inventor： Zhiqiang Yuan

IPC: G06V20/10 ,  G06V10/774 ,  G06V20/13 ,  G06T11/00 ,  G06V10/80 ,  G06V20/17 ,  G06T7/00 ,  G06N3/04

CPC classification number: G06V20/188 ,  G06V10/774 ,  G06V20/13 ,  G06T11/00 ,  G06V10/803 ,  G06V20/17 ,  G06T7/0012 ,  G06N3/0454 ,  G06T2207/20081 ,  G06T2207/10032 ,  G06T2207/30188 ,  G06T2200/24 ,  G06T2207/30252 ,  G06T2207/20084

Abstract: Implementations are described herein for conditioning a generator machine learning model to generate synthetic ground-level data that is biased towards a given agricultural area based on high-elevation images. In various implementations, a plurality of ground-level images may be accessed that depict crops within a specific agricultural area. A first set of high-elevation image(s) may also be accessed that depict the specific agricultural area. The ground-level images and the first set of high-elevation image(s) may be used to condition an air-to-ground generator machine learning model to generate synthetic ground-level data from high-elevation imagery depicting the specific agricultural area. A second set of high-elevation image(s) that depict a specific sub-region of the specific agricultural area may then be accessed and processed using the air-to-ground generator machine learning model to generate synthetic ground-level data that infers one or more conditions of the specific sub-region of the specific agricultural area.

公开(公告)号：US20230161890A1

公开(公告)日：2023-05-25

申请号：US17535457

申请日：2021-11-24

Applicant: X Development LLC

Inventor： Elliott Grant

IPC: G06F21/62 ,  G06F16/29 ,  G06N20/00

CPC classification number: G06F21/62 ,  G06F16/29 ,  G06N20/00 ,  G06F2221/2111

Abstract: Techniques are described herein for determining whether a particular user is authorized to access data, corresponding to a particular field, in a farmland database. A method includes: receiving a location history corresponding to a user, the location history including historical location data that indicate, for each time of a plurality of times, a location of the user at the time; applying the historical location data as inputs across a trained machine learning model to predict a persona corresponding to the user; receiving, from the user, a request to access data; in response to receiving the request to access the data, determining that the request is authorized based on the predicted persona corresponding to the user; and in response to determining that the request is authorized, providing access to the data.

公开(公告)号：US20230161308A1

公开(公告)日：2023-05-25

申请号：US17531410

申请日：2021-11-19

Applicant: X Development LLC

Inventor： Charles Nordstrom ,  Matthew Aaron Knoll ,  Neil Davé

IPC: G05B19/042

CPC classification number: G05B19/042 ,  G05B2219/2639 ,  G05B2219/2619

Abstract: A system for servicing watercraft includes one or more waterborne platforms. Each waterborne platform includes an electric power supply, a driving system for moving the waterborne platform in a body of water, a watercraft interfacing system configured to at least supply electric power to an electrically-powered watercraft, and a control interface configured to exchange data with a controller. The controller is configured to: receive input data, determine respective destination locations for the waterborne platforms to supply electric power to the electrically-powered watercraft, and send control data that includes data indicating the destination locations to the waterborne platforms.

公开(公告)号：US20230157262A1

公开(公告)日：2023-05-25

申请号：US18149840

申请日：2023-01-04

Applicant: X Development LLC

Inventor： Matthew Messana ,  Kyle James Cormany ,  Christopher Thornton ,  Barnaby John James ,  Neil Davé ,  Shane Washburn

IPC: A01K61/10 ,  B25J13/08 ,  A01K61/85 ,  B25J19/02 ,  A01K61/65 ,  G03B17/08

CPC classification number: A01K61/10 ,  B25J13/089 ,  B25J13/087 ,  A01K61/85 ,  B25J19/021 ,  A01K61/65 ,  B25J13/085 ,  G03B17/08

Abstract: A sensor positioning system, includes an actuation server for communicating with components of the sensor positioning system. The sensor positioning system additionally includes a first actuation system and a second actuation system, wherein each actuation system includes a pulley system for maneuvering an underwater sensor system. The sensor positioning system includes a dual point attachment bracket that connects through a first line to the first actuation system and connecting through a second line to the second actuation system. The underwater sensor system is affixed to the first pulley system, the second pulley system, and the dual attachment bracket through the first line and the second line.

公开(公告)号：US11657527B2

公开(公告)日：2023-05-23

申请号：US16424363

申请日：2019-05-28

Applicant: X Development LLC

Inventor： Yunfei Bai ,  Yuanzheng Gong

IPC: H04N5/268 ,  H04N5/247 ,  H04N5/232 ,  H04N13/111 ,  H04N13/161 ,  H04N13/282 ,  B25J9/16 ,  G06T7/12 ,  G06T7/521 ,  G06T7/13 ,  G06K9/62 ,  G06T5/00

CPC classification number: B25J9/1697 ,  B25J9/1661 ,  G06K9/6267 ,  G06T5/008 ,  G06T7/12 ,  G06T7/13 ,  G06T7/521 ,  H04N5/247 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10048

Abstract: Generating edge-depth values for an object, utilizing the edge-depth values in generating a 3D point cloud for the object, and utilizing the generated 3D point cloud for generating a 3D bounding shape (e.g., 3D bounding box) for the object. Edge-depth values for an object are depth values that are determined from frame(s) of vision data (e.g., left/right images) that captures the object, and that are determined to correspond to an edge of the object (an edge from the perspective of frame(s) of vision data). Techniques that utilize edge-depth values for an object (exclusively, or in combination with other depth values for the object) in generating 3D bounding shapes can enable accurate 3D bounding shapes to be generated for partially or fully transparent objects. Such increased accuracy 3D bounding shapes directly improve performance of a robot that utilizes the 3D bounding shapes in performing various tasks.

公开(公告)号：US11657498B2

公开(公告)日：2023-05-23

申请号：US16845189

申请日：2020-04-10

Applicant: X Development LLC

Inventor： Christopher Thornton ,  Matthew Messana ,  James Daniel Haley ,  Shane Washburn

IPC: G06K9/00 ,  G06T7/00 ,  A01K61/13 ,  H05B45/20 ,  A01K63/00 ,  A01K63/06 ,  H04N5/232

CPC classification number: G06T7/0012 ,  A01K61/13 ,  A01K63/003 ,  A01K63/06 ,  H04N5/232 ,  H05B45/20 ,  G06T2207/10028 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for a lighting controller for sea lice detection. In some implementations, fish are contained within an elliptical tank filled with water. An imaging station located on the elliptical tank is used to capture an image of a fish from which image analysis can be performed to detect sea lice or other skin features, including lesions, on the fish. Pairs of imaging assemblies coordinate pulsing light of at least a first and a second color and capturing images of the fish while the fish is illuminated by at least the first and the second color. By using the captured images with different color light, computers can detect features on the body of a fish including sea lice, skin lesions, shortened operculum or other physical deformities and skin features. Detection results can aid in mitigation techniques or be stored for analytics. For example, sea lice detection results can inform targeted treatments comprised of lasers, fluids, or mechanical devices such as a brush or suction.

公开(公告)号：US11654550B1

公开(公告)日：2023-05-23

申请号：US17097785

申请日：2020-11-13

Applicant: X Development LLC

Inventor： Paul Bechard ,  Matthew Bennice

IPC: B25J9/16 ,  B25J9/00

CPC classification number: B25J9/1605 ,  B25J9/0084

Abstract: Implementations are described herein for single iteration, multiple permutation robot simulation. In various implementations, one or more poses of a simulated object may be determined across one or more virtual environments. A plurality of simulated robots may be operated across the one or more virtual environments. For each simulated robot of the plurality of simulated robots, a camera transformation may be determined based on respective poses of the simulated robot and simulated object in the particular virtual environment. The camera transformation may be applied to the simulated object in the particular virtual environment of the one or more virtual environments in which the simulated robot operates. Based on the camera transformation, simulated vision data may be rendered that depicts the simulated object from a perspective of the simulated robot. Each of the plurality of simulated robots may be operated based on corresponding simulated vision data.

公开(公告)号：US20230154318A1

公开(公告)日：2023-05-18

申请号：US17527895

申请日：2021-11-16

Applicant: X Development LLC

Inventor： Christian Thieu Nguyen ,  Stefan Bogdanovic

IPC: G08G1/04 ,  G01R33/12 ,  G01R33/032

CPC classification number: G08G1/04 ,  G01R33/032 ,  G01R33/1284

Abstract: A traffic monitoring system includes an electron spin defect magnetometer in a vicinity of a roadway, the electron spin defect magnetometer configured to detect magnetic field signals induced by transit entities in the vicinity of the roadway. The electron spin defect magnetometer includes an electron spin defect body including a plurality of lattice point defects, an optical source arranged to excite the plurality of lattice point defects, and a photodetector arranged to receive photoluminescence emitted by the plurality of lattice point defects.

公开(公告)号：US20230154225A1

公开(公告)日：2023-05-18

申请号：US18155485

申请日：2023-01-17

Applicant: X Development LLC

Inventor： Barnaby John James ,  Evan Douglas Rapoport ,  Matthew Messana ,  Peter Kimball

IPC: G06V40/10 ,  G06N3/08 ,  A01K61/95 ,  G06T7/593 ,  G06T7/62 ,  G06V20/64

CPC classification number: G06V40/103 ,  G06N3/08 ,  A01K61/95 ,  G06T7/593 ,  G06T7/62 ,  G06V20/64 ,  G06T2207/10012 ,  G06T2207/20084

Abstract: Methods, systems, and apparatuses, including computer programs encoded on a computer-readable storage medium for estimating the shape, size, and mass of fish are described. A pair of stereo cameras may be utilized to obtain right and left images of fish in a defined area. The right and left images may be processed, enhanced, and combined. Object detection may be used to detect and track a fish in images. A pose estimator may be used to determine key points and features of the detected fish. Based on the key points, a three-dimensional (3-D) model of the fish is generated that provides an estimate of the size and shape of the fish. A regression model or neural network model can be applied to the 3-D model to determine a likely weight of the fish.

公开(公告)号：US20230154160A1

公开(公告)日：2023-05-18

申请号：US17986428

申请日：2022-11-14

Applicant: X Development LLC

Inventor： Mohi Khansari ,  Daniel Ho ,  Eric Jang ,  Yu Qing Du

IPC: G06V10/774 ,  G06T5/50

CPC classification number: G06V10/774 ,  G06T5/50 ,  G06T2207/20081

Abstract: Implementations disclosed herein relate to mitigating the reality gap through feature-level domain adaptation in training of a vision-based robotic action machine learning (ML) model. Implementations mitigate the reality gap through utilization of embedding consistency losses and/or action consistency losses during training of the action ML model.