Abstract: Systems and methods are provided for performing alignment calibration of an RF antenna in satellite communications. Data is received that is representative of inertial navigation system and gimbal angle measurement signals. The received data is collected while a vehicle is operated in a reduced yaw motion and while the RF antenna is tracking a satellite. Equations are used that describe a mathematical relationship among the misalignments, offsets, and latency mismatch to the antenna gimbal control servo measurements. Estimates are generated for certain errors involved in the alignment process. The generated estimates are provided for pointing the RF antenna.

Abstract: A signal generator outputs a reference signal corresponding to at least one wireless signal according to the predefined signal encoding to a channel emulator processor. The channel emulator processor is programmed to use at least one synthesized channel parameter and the reference signal to produce and store a perturbed signal as data for training machine learning and artificial intelligence systems. The synthesized channel parameter is synthesized using a channel synthesizer processor programmed to: ingest map elevation data, reference a transmitter and a receiver to the map elevation data, and perform ray tracing of a representative signal between the transmitter and the receiver, while applying at least one predetermined perturbation property to synthesize at least one channel parameter.

Abstract: The present invention is directed to systems and methods for detecting objects in a radar image stream. Embodiments of the invention can receive a data stream from radar sensors and use a deep neural network to convert the received data stream into a set of semantic labels, where each semantic label corresponds to an object in the radar data stream that the deep neural network has identified. Processing units running the deep neural network may be collocated onboard an airborne vehicle along with the radar sensor(s). The processing units can be configured with powerful, high-speed graphics processing units or field-programmable gate arrays that are low in size, weight, and power requirements. Embodiments of the invention are also directed to providing innovative advances to object recognition training systems that utilize a detector and an object recognition cascade to analyze radar image streams in real time.

Abstract: Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images.

Abstract: Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images.

Abstract: Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images.

Abstract: Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images.

Abstract: Embodiments of the present disclosure relate to an electric motor drive system for driving a low-voltage motor. The low-voltage motor includes a rotor and a stator that comprises a number of single-turn coils. A motor drive controller can control the low-voltage motor. The motor drive controller includes a current source inverter. The current source inverter includes driver circuitry configured to generate switching commands, a variable current source and motor commutation circuitry. The variable current source can generate a variable current that regulates power in the low-voltage motor. The motor commutation circuitry receives the variable current and switching commands, and commutates phase currents that are output to the low-voltage motor.

Abstract: A cable containing an optical fiber is used to transmit data between an underwater remotely operated vehicle (ROV) and a support vessel floating on the surface of the water. The ROV stores the cable on a spool and releases the cable into the water as the ROV dives away from the support vessel. The ROV detects the tension in the cable and the rate that the cable is released from the ROV is proportional to the detected tension in the cable. After the ROV has completed the dive and retrieved by the support vessel, the cable can be retrieved from the water and rewound onto the spool in the ROV.

Abstract: Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images.

Abstract: Systems and methods are provided for an underbody blast structure. The underbody blast structure includes at least one hanger to couple to a vehicle. The underbody blast structure also includes a housing coupled to the at least one hanger. The housing includes a first protection plate opposite a second protection plate. The first protection plate and the second protection plate are to protect the vehicle. The first protection plate is spaced apart from the second protection plate by a plurality of interconnecting members. The plurality of interconnecting members defines a plurality of channels between the first protection plate and the second protection plate. At least one of the plurality of channels is adapted to receive a portion of a suspension system of the vehicle.

Abstract: Methods and systems are provided for detecting a defect in a solar panel. The method includes initially imaging, via an infrared camera, a group of solar panels. Then, identifying, via a computer system configured for solar panel defect detection, the individual solar panels in the group of solar panels. Finally, identifying, via evaluation of an infrared image obtained by the infrared camera, a defect in at least one of the group of solar panels.

Abstract: A slide for a weapon conversion kit of the type used in conjunction with a firearm having a stock ejector and configured to fire ammunition is provided. The slide includes a slide body and a slaved ejector member rotatably coupled to the slide body. The slaved ejector member has a first portion and a second portion, the second portion including a contact region. The slaved ejector member is configured to contact the stock ejector when the slide body slides rearward in response to firing of the firearm and thereby causes the contact region of the second portion of the slaved ejector member to eject a cartridge case of the ammunition.

Abstract: A conversion kit for a firearm of the type having a removable component is disclosed. The conversion kit includes a chamber piece having a coupling end, and a muzzle piece of a conversion barrel having a coupling end configured to be secured to the coupling end of the chamber piece and an engagement end. The engagement end is configured to mate with the removable component such that manipulation of the removable component causes the coupling end of the muzzle piece of the conversion barrel to be secured to the coupling end of the chamber piece.

Abstract: A container (e.g., an ammunition casing, a rocket housing, or the like) includes a body structure having a wall defining a cavity configured to accept an energetic material, the body structure having a central region situated longitudinally between a first side region and a second side region, wherein the wall within the central region has a thickness that is less than the thickness of the wall within first region and either less than or equal to the thickness within the second side region. A strength reduction pattern is formed at least partially within the central region of the wall such that the strength reduction pattern provides a preferred rupture path when the energetic material is subjected to a predetermined external stimulus.

Abstract: A floatable land vehicle is provided that includes a base body having at least one buoyancy body that is detachably fastened to the base body, the buoyancy body containing an at least partially filled tank.

Abstract: A flow-through card rail module is provided in a circuit module chassis assembly for an embedded computing system. A set of elongated guide rails are formed on a base plate and define a card channel for receiving a circuit card. Each guide rail has a cooling passage extending from a fluid inlet to a fluid outlet. A corrugated structure is formed on an opposite side of the base plate and includes a set of elongated cells. Each elongated cell has a cooling passage formed therein extending from the fluid inlet to the fluid outlet. Internal walls subdivide the cooling passages formed in the guide rails and the elongated cells to form a honeycomb structure. The flow-through card rail module including the base plate, the guide rails and the corrugated structure may be formed as a monolithic component.

Abstract: A method and an assembly for absorbing energy during an overload event. An energy absorber reduces loads on an object being transported on a loading unit during a single overload event, which introduces such a high degree of energy that there is an overwhelming likelihood the object would be damaged without an energy absorber. Measurement values on the current state of the loading unit are sensed. A control device determines an overload event and a damping of the energy absorber is set to a high value after the detection of the overload event. The damping is maintained for a specified prolonged time period and controlled dependent on the measurement values during the overload event to increase the load for objects during the specified time period initially to a specified threshold load and after the specified time dependent on the measurement values detected during the overload event.

Abstract: An ammunition primer assembly is provided that includes, but is not limited to a cup having a base and a sidewall, a priming composition located in the cup and disposed on the base, an anvil located in the cup an upper surface, a lower surface and a side surface abutting the sidewall. The anvil defining a central channel formed therethrough. A portion of the base of the cup forms a striking surface. The striking surface is adjacent to a portion of the primer composition that is adjacent to the lower surface of the anvil. The striking surface is offset from a center of the cup.

Abstract: A vessel, such as a rocket motor tube, comprised of an insert, and a joint that allows the insert to decouple from the vessel to relieve pressure when subjected to excessive temperatures and/or a predetermined temperature or temperature range.