公开(公告)号：US20230266753A1

公开(公告)日：2023-08-24

申请号：US17961382

申请日：2022-10-06

Applicant: The Government of the United States of America, as represented by the Secretary of the Navy

Inventor： Blake J. Landry ,  William David Null

IPC: G05D1/00

CPC classification number: G05D1/0016 ,  G05D1/0022 ,  G05D1/0088 ,  G05D2201/0207

Abstract: A system having a networking device, a plurality of processing devices, and one or more unmanned devices, wherein each unmanned device couples to a corresponding one of the processing devices, wherein each unmanned device comprises one or more operational components. The system having a controller device configured to control at least one of the one or more unmanned devices via the networking device and the corresponding one of the processing devices, the controller device comprising one of the processing devices, wherein the controlled at least one unmanned device is configurable via the corresponding processing device in a control operating mode or in a robot operating mode, the control operating mode enabling the associated unmanned device to perform commands received from the controller device via the corresponding processing device, and the robot operating mode enabling the unmanned device to receive programmable instructions from the controller device via the corresponding processing device.

公开(公告)号：US11712802B2

公开(公告)日：2023-08-01

申请号：US16884669

申请日：2020-05-27

Applicant: Boston Dynamics, Inc.

Inventor： Joel Chestnutt ,  Gina Fay

IPC: B25J9/16 ,  G05D1/02 ,  G05D1/08 ,  B25J19/02

CPC classification number: B25J9/1664 ,  B25J19/021 ,  G05D1/0212 ,  G05D1/08 ,  G05D2201/0207

Abstract: A method includes receiving sensor data of an environment about a robot and generating a plurality of waypoints and a plurality of edges each connecting a pair of the waypoints. The method includes receiving a target destination for the robot to navigate to and determining a route specification based on waypoints and corresponding edges for the robot to follow for navigating the robot to the target destination selected from waypoints and edges previously generated. For each waypoint, the method includes generating a goal region encompassing the corresponding waypoint and generating at least one constraint region encompassing a goal region. The at least one constraint region establishes boundaries for the robot to remain within while traversing toward the target destination. The method includes navigating the robot to the target destination by traversing the robot through each goal region while maintaining the robot within the at least one constraint region.

公开(公告)号：US11688275B2

公开(公告)日：2023-06-27

申请号：US17521016

申请日：2021-11-08

Applicant: Honeywell International Inc.

Inventor： Scott Lang ,  Johan Vossen ,  Rich Lau ,  Donna Burns

IPC: G08B29/14 ,  G08B17/06 ,  G05D1/00 ,  G08B17/107 ,  G05D1/02

CPC classification number: G08B29/145 ,  G05D1/0094 ,  G05D1/0214 ,  G08B17/06 ,  G08B17/107 ,  G05D2201/0207

Abstract: Methods, devices, and systems for an unmanned system (US) for smoke detector testing are described herein. In some examples, one or more embodiments include a test kit, a processor, and a memory having instructions stored thereon which, when executed by the processor, cause the processor to perform a test procedure on a projected beam smoke detector in a facility using the test kit and communicate a result of the test procedure to a smoke detector network associated with the facility.

公开(公告)号：US11687089B2

公开(公告)日：2023-06-27

申请号：US16651139

申请日：2018-07-11

Applicant: SONY CORPORATION

Inventor： Ryo Takahashi ,  Chao Wang ,  Dai Kobayashi ,  Masataka Toyoura

IPC: G05D1/02

CPC classification number: G05D1/0274 ,  G05D1/0217 ,  G05D1/0238 ,  G05D2201/0207

Abstract: Information regarding an obstacle region and information regarding an empty region are optimally updated to minimize an information amount. In the obstacle region, an obstacle exists in space where a mobile body moves. In the empty region, an obstacle does not exist. According to the disclosure, there is provided an environmental information update apparatus including an update unit that updates information regarding an obstacle region and information regarding an empty region, an obstacle existing in space where a mobile body moves in the obstacle region, the obstacle not existing in the empty region, in which the update unit updates the obstacle region, and updates the empty region on the basis of different periods of elapsed time.

公开(公告)号：US11674288B2

公开(公告)日：2023-06-13

申请号：US16599380

申请日：2019-10-11

Applicant: Deere & Company

Inventor： Noel W. Anderson ,  Zachary T. Bonefas

IPC: A01B69/04 ,  G01N15/02 ,  E02F9/20 ,  G01W1/02 ,  E02F9/26 ,  G05D1/02 ,  G05D1/00 ,  G07C5/00 ,  A01D41/127 ,  G01N15/06 ,  G01N33/00 ,  G01N15/00

CPC classification number: E02F9/205 ,  A01B69/008 ,  A01D41/1278 ,  E02F9/2054 ,  E02F9/262 ,  G01N15/0227 ,  G01N15/06 ,  G01N33/0063 ,  G01W1/02 ,  G05D1/0022 ,  G05D1/0212 ,  G05D1/0219 ,  G07C5/008 ,  G01N2015/0046 ,  G01N2015/0693 ,  G01N2033/0068 ,  G05D2201/0207

Abstract: In accordance with an example embodiment, a system and method for obscurant mitigation is disclosed. The system comprises an obscurant assessor configured to characterize one or more characteristics of a detected obscurant and generate an obscurant model; an obscurant mitigator configured to perform one or more mitigation operations; and a controller communicatively coupled to each of the obscurant assessor and the obscurant mitigator. The controller is configured to receive an output signal from a vehicle sensor corresponding to a detected obscurant level and determine if the detected obscurant level exceeds a predetermined threshold. The controller generates an obscurant mitigation plan if the detected obscurant level exceeds the predetermined threshold based on the obscurant model generated by the obscurant assessor; and controls operations of an obscurant mitigator based on the obscurant mitigation plan to reduce the detected obscurant level.

公开(公告)号：US11645846B2

公开(公告)日：2023-05-09

申请号：US17836147

申请日：2022-06-09

Applicant: Anhui Polytechnic University

Inventor： Mengyuan Chen ,  Lingmei Ding

IPC: G06V20/00 ,  G06V20/40 ,  G06T7/70 ,  G05D1/02

CPC classification number: G06V20/46 ,  G05D1/0219 ,  G05D1/0246 ,  G06T7/70 ,  G05D2201/0207

Abstract: A closed-loop detecting method using an inverted index-based key frame selection strategy, storage media and apparatus are provided. The method includes following steps: step I: acquiring image information at a current position, processing the image information to extract corresponding image features therefrom and solve a camera pose; step II: capturing image features successively during movement of a robot, as consecutive image frames, performing, on the consecutive image frames, an indexing, in which the inverted index-based key frame selection strategy is introduced into a key frame selection strategy to supplement key frames which are prone to be missed in a conventional forward indexing during a curvilinear movement of the robot; and step III: performing closed-loop detection and correction of accumulative errors based on image features carried by key frames.

公开(公告)号：US20190236732A1

公开(公告)日：2019-08-01

申请号：US16262708

申请日：2019-01-30

Applicant: ImageKeeper LLC

Inventor： Jerry Speasl ,  Mike Patterson ,  Marc Roberts

IPC: G06Q50/16 ,  H04L9/32 ,  G01C21/20 ,  G05D1/00 ,  G05D1/10 ,  G05D1/02 ,  B64C39/02

CPC classification number: G06Q50/163 ,  B64C39/024 ,  B64C2201/12 ,  G01C21/206 ,  G05D1/0088 ,  G05D1/0219 ,  G05D1/101 ,  G05D2201/0207 ,  H04L9/3242 ,  H04L9/3247

Abstract: Media data about a property is collected via one or more unmanned vehicles having sensors, and optionally other devices as well. The unmanned vehicles are guided along paths about the property, optionally about the exterior and interior of a structure on the property, A layout of the property—optionally including a layout of the interior and/or exterior of the structure—is generated and shared. The media data and the generated layout may be certified using digital signatures, enabling verification of their source device, collection time, and authenticity.

公开(公告)号：US20190220025A1

公开(公告)日：2019-07-18

申请号：US15869291

申请日：2018-01-12

Applicant: PIXART IMAGING INC.

Inventor： KAI-SHUN CHEN ,  WEI-CHUNG WANG

IPC: G05D1/02 ,  G06K9/00

CPC classification number: G05D1/0214 ,  G05D1/0238 ,  G05D1/0246 ,  G05D2201/0203 ,  G05D2201/0207 ,  G06K9/00805

Abstract: The disclosure is related to a method and a system for obstacle detection adapted to a self-guiding machine. The method is performed in the system including a controller for driving the system, a light emitter, a light sensor, an image processor and a central processor. The light emitter and the light sensor are set apart at a distance. When the light emitter emits an indicator light being projected onto a path the self-guiding machine travels toward, the light sensor senses the indicator light. An image containing the indicator light is generated. After analyzing the image, at least one feature of the indicator light being sensed can be obtained and used to obtain a spatial relationship between the self-guiding machine and an obstacle. The spatial relationship allows the system to determine if the self-guiding machine will collide with a wall or fall from a cliff.

公开(公告)号：US20190056751A1

公开(公告)日：2019-02-21

申请号：US16047598

申请日：2018-07-27

Applicant: Nuro, Inc.

Inventor： David Ferguson ,  Jiajun Zhu ,  Nan Ransohoff ,  Pichayut Jirapinyo

IPC: G05D1/02 ,  A47J37/06 ,  A23L2/52 ,  A23L7/109 ,  H05B6/68 ,  B60P3/025 ,  B60P3/00 ,  G01C21/34

CPC classification number: G06Q10/0837 ,  A23L2/52 ,  A23L5/00 ,  A23L7/109 ,  A23V2002/00 ,  A47J37/0658 ,  B60H1/00364 ,  B60H1/00735 ,  B60P1/36 ,  B60P3/007 ,  B60P3/0257 ,  B60R19/18 ,  B60R19/483 ,  B60R21/34 ,  B60R21/36 ,  B60R25/25 ,  B60R25/252 ,  B60R2021/346 ,  B65G67/24 ,  G01C21/20 ,  G01C21/343 ,  G01C21/3438 ,  G01C21/3453 ,  G05D1/0027 ,  G05D1/0033 ,  G05D1/0038 ,  G05D1/0061 ,  G05D1/0088 ,  G05D1/0094 ,  G05D1/0212 ,  G05D1/0214 ,  G05D1/0223 ,  G05D1/0231 ,  G05D1/0276 ,  G05D1/0291 ,  G05D1/12 ,  G05D2201/0207 ,  G05D2201/0213 ,  G06F3/0484 ,  G06F16/955 ,  G06K7/10297 ,  G06K7/10722 ,  G06K7/1413 ,  G06K9/00201 ,  G06K9/00791 ,  G06K19/06028 ,  G06K19/0723 ,  G06N20/00 ,  G06Q10/0631 ,  G06Q10/06315 ,  G06Q10/0635 ,  G06Q10/083 ,  G06Q10/0832 ,  G06Q10/0833 ,  G06Q10/0834 ,  G06Q10/0835 ,  G06Q10/08355 ,  G06Q20/00 ,  G06Q20/127 ,  G06Q20/18 ,  G06Q30/0266 ,  G06Q30/0631 ,  G06Q30/0645 ,  G06Q50/12 ,  G06Q50/28 ,  G06Q50/30 ,  G07F17/0057 ,  G07F17/12 ,  G08G1/04 ,  G08G1/202 ,  G08G1/22 ,  H04L67/12 ,  H04N5/76 ,  H04W4/024 ,  H04W4/40 ,  H05B6/688

Abstract: An autonomous robot vehicle in accordance with aspects of the present disclosure includes a conveyance system, a navigation system, a communication system configured to communicate with a food delivery management system, one or more storage modules including a storage compartment or a storage sub-compartment configured to store food items, one or more preparation modules including a preparation compartment or a preparation sub-compartment configured to prepare the food items, processor(s), and a memory storing instructions. The instructions, when executed by the processor(s), cause the autonomous robot vehicle to, autonomously, receive via the communication system a food order for a destination, determine a travel route that includes the destination, control the conveyance system to travel the travel route to reach the destination, and prepare the food item while traveling on the travel route.

公开(公告)号：US20190035096A1

公开(公告)日：2019-01-31

申请号：US15712152

申请日：2017-09-22

Applicant: SHENZHEN UNIVERSITY

Inventor： Hui HUANG ,  Kai XU

IPC: G06T7/50 ,  G05D1/00 ,  G05D1/02 ,  B25J19/02 ,  B25J9/16

CPC classification number: G06T7/50 ,  B25J9/1664 ,  B25J19/023 ,  G05D1/0094 ,  G05D1/0246 ,  G05D2201/0207 ,  G06T2207/10024 ,  G06T2207/10028 ,  Y10S901/01

Abstract: A method of scene reconstruction includes: a depth image taken by a camera mounted on a robot is acquired, and a current tensor field key frame is generated based on the depth image; spatial-temporal interpolation is performed on the current tensor field key frame and a previous tensor field key frame to obtain an interpolated tensor field key frame; a robot planning path is acquired by particle advection algorithm according to the current tensor field key frame, the previous tensor field key frame, and the interpolated tensor field key frame; a camera planning path is acquired according to the robot planning path and an energy equation of the camera; and a scene is reconstructed according to the depth images captured by the camera.