公开(公告)号：US20240404271A1

公开(公告)日：2024-12-05

申请号：US18800296

申请日：2024-08-12

Applicant: Tomahawk Robotics, Inc.

Inventor： William S. BOWMAN ,  Sean WAGONER ,  Andrew D. FALENDYSZ ,  Matthew D. SUMMER ,  Kevin MAKOVY ,  Jeffrey S. COOPER ,  Brad TRUESDELL

IPC: G06V10/96 ,  G05B13/02 ,  G06V10/70 ,  G06V10/764 ,  G06V10/94 ,  G06V20/56

Abstract: Methods and systems are described herein for hosting and arbitrating algorithms for the generation of structured frames of data from one or more sources of unstructured input frames. A plurality of frames may be received from a recording device and a plurality of object types to be recognized in the plurality of frames may be determined. A determination may be made of multiple machine learning models for recognizing the object types. The frames may be sequentially input into the machine learning models to obtain a plurality of sets of objects from the plurality of machine learning models and object indicators may be received from those machine learning models. A set of composite frames with the plurality of indicators corresponding to the plurality of objects may be generated, and an output stream may be generated including the set of composite frames to be played back in chronological order.

公开(公告)号：US20250086831A1

公开(公告)日：2025-03-13

申请号：US18959555

申请日：2024-11-25

Applicant: Tomahawk Robotics, Inc.

Inventor： Daniel R. HEDMAN ,  Matthew D. SUMMER ,  William S. BOWMAN ,  Michael E. BOWMAN ,  Brad TRUESDELL ,  Andrew D. FALENDYSZ

IPC: G06T7/73 ,  G06T7/60 ,  G06V10/774 ,  G06V20/17 ,  G06V40/20 ,  H04N7/18 ,  H04N23/661

Abstract: Methods and systems are described herein for determining three-dimensional locations of objects within identified portions of images. An image processing system may receive an image and an identification of location within an image. The image may be input into a machine learning model to detect one or more objects within the identified location. Multiple images may then be used to generate location estimations of those objects. Based on the location estimations, an accurate three-dimensional location may be calculated.

公开(公告)号：US20250022167A1

公开(公告)日：2025-01-16

申请号：US18350722

申请日：2023-07-11

Applicant: Tomahawk Robotics, Inc.

Inventor： Daniel R. HEDMAN ,  Matthew D. SUMMER ,  William S. BOWMAN ,  Michael E. BOWMAN ,  Brad TRUESDELL ,  Andrew D. FALENDYSZ

IPC: G06T7/73 ,  G05D1/10 ,  G06T7/60 ,  G06V10/774 ,  G06V20/17 ,  G06V40/20 ,  H04N7/18 ,  H04N23/661

Abstract: Methods and systems are described herein for determining three-dimensional locations of objects within identified portions of images. An image processing system may receive an image and an identification of location within an image. The image may be input into a machine learning model to detect one or more objects within the identified location. Multiple images may then be used to generate location estimations of those objects. Based on the location estimations, an accurate three-dimensional location may be calculated.

公开(公告)号：US20240378880A1

公开(公告)日：2024-11-14

申请号：US18772099

申请日：2024-07-12

Applicant: Tomahawk Robotics, Inc.

Inventor： William S. BOWMAN ,  Sean WAGONER ,  Andrew D. FALENDYSZ ,  Matthew D. SUMMER ,  Kevin MAKOVY ,  Jeffrey S. COOPER ,  Brad TRUESDELL

IPC: G06V10/96 ,  G05B13/02 ,  G06V10/70 ,  G06V10/764 ,  G06V10/94 ,  G06V20/56

Abstract: Methods and systems are described herein for hosting and arbitrating algorithms for the generation of structured frames of data from one or more sources of unstructured input frames. A plurality of frames may be received from a recording device and a plurality of object types to be recognized in the plurality of frames may be determined. A determination may be made of multiple machine learning models for recognizing the object types. The frames may be sequentially input into the machine learning models to obtain a plurality of sets of objects from the plurality of machine learning models and object indicators may be received from those machine learning models. A set of composite frames with the plurality of indicators corresponding to the plurality of objects may be generated, and an output stream may be generated including the set of composite frames to be played back in chronological order.

公开(公告)号：US20240005801A1

公开(公告)日：2024-01-04

申请号：US18469635

申请日：2023-09-19

Applicant: Tomahawk Robotics

Inventor： Matthew D. SUMMER ,  William S. BOWMAN ,  Andrew D. FALENDYSZ ,  Daniel R. HEDMAN ,  Brad TRUESDELL ,  Jeffrey S. COOPER ,  Michael E. BOWMAN ,  Sean WAGONER ,  Kevin MAKOVY

IPC: G08G5/00 ,  B64C39/02

CPC classification number: G08G5/003 ,  B64C39/024 ,  G08G5/0004 ,  B64U2101/30

Abstract: A common command and control architecture (alternatively termed herein as a “universal control architecture”) is disclosed that allows different unmanned systems, including different types of unmanned systems (e.g., air, ground, and/or maritime unmanned systems), to be controlled simultaneously through a common control device (e.g., a controller that can be an input and/or output device). The universal control architecture brings significant efficiency gains in engineering, deployment, training, maintenance, and future upgrades of unmanned systems. In addition, the disclosed common command and control architecture breaks the traditional stovepipe development involving deployment models and thus reducing hardware and software maintenance, creating a streamlined training/proficiency initiative, reducing physical space requirements for transport, and creating a scalable, more connected interoperable approach to control of unmanned systems over existing unmanned systems technology.

公开(公告)号：US20230394812A1

公开(公告)日：2023-12-07

申请号：US18454055

申请日：2023-08-22

Applicant: Tomahawk Robotics

Inventor： William S. BOWMAN ,  Sean WAGONER ,  Andrew D. FALENDYSZ ,  Matthew D. SUMMER ,  Kevin MAKOVY ,  Jeffrey S. COOPER ,  Brad TRUESDELL

IPC: G06V10/96 ,  G06V10/70 ,  G06V10/94 ,  G06V10/764 ,  G06V20/56 ,  G05B13/02

CPC classification number: G06V10/96 ,  G06V10/87 ,  G06V10/955 ,  G06V10/764 ,  G06V20/56 ,  G05B13/0265

Abstract: Methods and systems are described herein for hosting and arbitrating algorithms for the generation of structured frames of data from one or more sources of unstructured input frames. A plurality of frames may be received from a recording device and a plurality of object types to be recognized in the plurality of frames may be determined. A determination may be made of multiple machine learning models for recognizing the object types. The frames may be sequentially input into the machine learning models to obtain a plurality of sets of objects from the plurality of machine learning models and object indicators may be received from those machine learning models. A set of composite frames with the plurality of indicators corresponding to the plurality of objects may be generated, and an output stream may be generated including the set of composite frames to be played back in chronological order.