利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

23 条记录 (耗时 0.019 秒)

    Using machine learning techniques to estimate available energy for vehicles
    12.
    发明授权
    Using machine learning techniques to estimate available energy for vehicles 有权

    公开(公告)号：US11592824B2

    公开(公告)日：2023-02-28

    申请号：US17387131

    申请日：2021-07-28

    申请人： WING Aviation LLC

    发明人： Kaiwen Gu ,  Matthew Nubbe

    IPC分类号： G05D1/02 ,  B60L58/12 ,  G06N3/08 ,  G06N20/00 ,  G05D1/00 ,  G01C21/34 ,  G06N5/04 ,  G06N5/046

    摘要： Controlling a vehicle according to a trained neural network model capable of being used to generate an output from which one or more vehicle operating variables can be estimated. The neural network model can be used to process, as input, aggregated data corresponding to operational and/or environmental characteristics experienced by the vehicle during at least a portion of a voyage. The aggregated data can include a range of values collected over a period of time when the vehicle is traversing the portion of the voyage. The output generated by the neural network model, based on processing the input, can be further processed in order to determine, for example, an estimated state of charge and/or an estimated remaining flight time for the vehicle. Such estimated values can thereafter be used by a controller of the vehicle to maintain course or maneuver to a charging station.

    Anticipatory Dispatch of UAVs to Pre-staging Locations
    13.
    发明申请
    Anticipatory Dispatch of UAVs to Pre-staging Locations 有权

    公开(公告)号：US20220137646A1

    公开(公告)日：2022-05-05

    申请号：US17647808

    申请日：2022-01-12

    申请人： Wing Aviation LLC

    发明人： Jesse Blake ,  James Schmalzried ,  Scott Velez ,  Andre Prager ,  Eric Teller ,  Matthew Nubbe

    IPC分类号： G05D1/10 ,  B64C39/02 ,  G05D1/00 ,  G06Q50/30 ,  G06Q10/06 ,  G06Q10/08

    摘要： An example method involves determining an expected demand level for a first type of a plurality of types of transport tasks for unmanned aerial vehicles (UAVs), the first type of transport tasks associated with a first payload type. Each of the UAVs is physically reconfigurable between at least a first and a second configuration corresponding to the first payload type and a second payload type, respectively. The method also involves determining based on the expected demand level for the first type of transport tasks, (i) a first number of UAVs having the first configuration and (ii) a second number of UAVs having the second configuration. The method further involves, at or near a time corresponding to the expected demand level, providing one or more UAVs to perform the transport tasks, including at least the first number of UAVs.

    USING MACHINE LEARNING TECHNIQUES TO ESTIMATE AVAILABLE ENERGY FOR VEHICLES
    14.
    发明申请
    USING MACHINE LEARNING TECHNIQUES TO ESTIMATE AVAILABLE ENERGY FOR VEHICLES 有权

    公开(公告)号：US20210356967A1

    公开(公告)日：2021-11-18

    申请号：US17387131

    申请日：2021-07-28

    申请人： WING Aviation LLC

    发明人： Kaiwen Gu ,  Matthew Nubbe

    IPC分类号： G05D1/02 ,  B60L58/12 ,  G06N3/08 ,  G06N20/00 ,  G05D1/00 ,  G01C21/34 ,  G06N5/04

    摘要： Controlling a vehicle according to a trained neural network model capable of being used to generate an output from which one or more vehicle operating variables can be estimated. The neural network model can be used to process, as input, aggregated data corresponding to operational and/or environmental characteristics experienced by the vehicle during at least a portion of a voyage. The aggregated data can include a range of values collected over a period of time when the vehicle is traversing the portion of the voyage. The output generated by the neural network model, based on processing the input, can be further processed in order to determine, for example, an estimated state of charge and/or an estimated remaining flight time for the vehicle. Such estimated values can thereafter be used by a controller of the vehicle to maintain course or maneuver to a charging station.

    Using machine learning techniques to estimate available energy for vehicles
    15.
    发明授权
    Using machine learning techniques to estimate available energy for vehicles 有权

    公开(公告)号：US11119494B2

    公开(公告)日：2021-09-14

    申请号：US16241204

    申请日：2019-01-07

    申请人： Wing Aviation LLC

    发明人： Kaiwen Gu ,  Matthew Nubbe

    IPC分类号： G05D1/02 ,  B60L58/12 ,  G06N3/08 ,  G06N20/00 ,  G05D1/00 ,  G01C21/34 ,  G06N5/04

    摘要： Controlling a vehicle according to a trained neural network model capable of being used to generate an output from which one or more vehicle operating variables can be estimated. The neural network model can be used to process, as input, aggregated data corresponding to operational and/or environmental characteristics experienced by the vehicle during at least a portion of a voyage. The aggregated data can include a range of values collected over a period of time when the vehicle is traversing the portion of the voyage. The output generated by the neural network model, based on processing the input, can be further processed in order to determine, for example, an estimated state of charge and/or an estimated remaining flight time for the vehicle. Such estimated values can thereafter be used by a controller of the vehicle to maintain course or maneuver to a charging station.

    Distribution of Aerial Vehicle Transport Capacity
    16.
    发明申请
    Distribution of Aerial Vehicle Transport Capacity 审中-公开

    公开(公告)号：US20190197643A1

    公开(公告)日：2019-06-27

    申请号：US15852872

    申请日：2017-12-22

    申请人： Wing Aviation LLC

    发明人： Theran Cochran ,  Matthew Nubbe ,  Kevin Jenkins

    IPC分类号： G06Q50/28 ,  B64C39/02 ,  G06Q10/06

    CPC分类号： G06Q50/28 ,  B64C39/024 ,  B64C2201/104 ,  B64C2201/108 ,  B64C2201/128 ,  G06Q10/06315 ,  G06Q10/06393

    摘要： Disclosed herein are methods and systems that can help an aerial transport service provider (ATSP) determine how to distribute and redistribute unmanned aerial vehicles (UAVs) amongst a plurality of UAV deployment stations located throughout a geographic area. In accordance with example embodiments, the ATSP system can take one or more performance metrics for item providers into account when determining how much UAV transport capacity to allocate to different item providers for a given time period. The ATSP can then determine how to distribute UAVs amongst different UAV nests in advance of and/or during the given time period, such that each item provider's allocated UAV transport capacity is available from the UAV nest or nest(s) that serve each item provider during the given time period.

    Multi-UAV management
    19.
    发明授权
    Multi-UAV management 有权

    公开(公告)号：US11691755B2

    公开(公告)日：2023-07-04

    申请号：US15953831

    申请日：2018-04-16

    申请人： Wing Aviation LLC

    发明人： Kaiwen Gu ,  Matthew Nubbe

    IPC分类号： B64D45/00 ,  B64C39/02 ,  G05D1/10 ,  B64U101/60

    CPC分类号： B64D45/00 ,  B64C39/024 ,  G05D1/104 ,  B64D2045/0085 ,  B64U2101/60

    摘要： Aspects of the disclosure relate to identifying and responding to problem conditions for a fleet of aerial vehicles. This may include receiving at one or more processors of one or more server computing devices sensor feedback from an AV of the fleet. A problem condition may be identified using the sensor feedback. A mitigation response for the problem condition relating to a mission assigned to the aerial vehicle may be determined. The mitigation response may be sent to the AV in order to cause the aerial vehicle to maneuver according to the mitigation response and thereby automatically respond to the problem condition.

    Systems and methods for battery capacity management in a fleet of UAVs
    20.
    发明授权
    Systems and methods for battery capacity management in a fleet of UAVs 有权

    公开(公告)号：US11565605B2

    公开(公告)日：2023-01-31

    申请号：US17083293

    申请日：2020-10-29

    申请人： Wing Aviation LLC

    发明人： Matthew Nubbe

    IPC分类号： B60L58/13 ,  G01R31/387 ,  B64C39/02 ,  G01R31/392 ,  B60L58/16

    摘要： A method includes determining a threshold capacity associated with at least a first unmanned aerial vehicle (UAV) and a second UAV. The method includes initially setting a target charge voltage of a first battery of the first UAV to less than a full charge voltage to limit a state of charge of the first battery based on the threshold capacity. The method includes, over a lifetime of the first battery of the first UAV, periodically comparing a full charge capacity of the first battery to the threshold capacity. The method includes, based on the comparing, periodically adjusting the target charge voltage of the first battery, such that, as the full charge capacity of the first battery decreases with age, the target charge voltage increases towards the full charge voltage of the first battery.