Inflatable and deployable mast fairings for submarine sail systems

    公开(公告)号:US12227276B1

    公开(公告)日:2025-02-18

    申请号:US17840660

    申请日:2022-06-15

    Abstract: An inflatable deployable mast fairing assembly is provided with a rigid foundation, a hydrodynamic fairing and at least one soft actuator. The hydrodynamic fairing is shaped to close an aperture formed between a deployable hardware system and a sail bay opening. A first soft actuator connects to the rigid foundation at one end and to the hydrodynamic fairing at another. Fluid pressurization elongates a first soft actuator coaxial to the deployable hardware system to fittedly position the fairing in the aperture with a void in the fairing to receive the hardware system. If the rigid foundation is sail-mounted, a second soft actuator connects to the sail-mounted foundation opposite the first soft actuator and to a counter flange mechanically connected to the hydrodynamic fairing. A second pressurization elongates the second soft actuator coaxial to the deployable hardware system to retract the hydrodynamic fairing from the aperture.

    System and Method for Closed-Loop Uncertainty for Human-Machine Teamwork

    公开(公告)号:US20250036982A1

    公开(公告)日:2025-01-30

    申请号:US18783788

    申请日:2024-07-25

    Abstract: A method that includes receiving user input associated with identifying a threshold point associated with a classification task, identifying, a machine learning model, in the first set of visual data, a machine placement candidate point associated with identifying the threshold point, and identifying, based on the machine placement candidate point, a set of baseline confidence values via a baseline uncertainty model. The method includes training the machine learning model based on a determined state space by identifying, subsequent sets of visual data additional threshold points, receiving user feedback indicating an accuracy, comparing the baseline confidence values with locations associated with the additional threshold points, generating reward values based on an identified amount of error, and configuring the machine learning model based on the reward values. The method includes identifying in a second set of visual data, via the trained machine learning model, a visual feature associated with the classification task.

Patent Agency Ranking