Abstract: Approaches provide for performance of a complex (e.g., compound) task that may involve multiple discrete tasks not obvious from an instruction to perform the complex task. A set of conditions for an environment can be determined using captured image data, and the instruction analyzed to determine a set of final conditions to exist in the environment after performance of the instruction. These initial and end conditions are used to determine a sequence of discrete tasks to be performed to cause a robot or automated device to perform the instruction. This can involve use of a symbolic or visual planner in at least some embodiments, as well as a search of possible sequences of actions available for the robot or automated device. A robot can be caused to perform the sequence of discrete tasks, and feedback provided such that the sequence of tasks can be modified as appropriate.

Abstract: Approaches presented herein provide for a framework to integrate human provided feedback in natural language to update a robot planning cost or value. The natural language feedback may be modeled as a cost or value associated with completing a task assigned to the robot. This cost or value may then be added to an initial task cost or value to update one or more actions to be performed by the robot. The framework can be applied to both real work and simulated environments where the robot may receive instructions, in natural language, that either provide a goal, modify an existing goal, or provide constraints to actions to achieve an existing goal.

Abstract: Systems and methods for detecting anomalies in antenna systems (e.g., air traffic control surveillance systems), include a processor receiving antenna status information. A variational autoencoder receives and optimizes the antenna status information and determines whether it qualifies as an anomaly. Optimized antenna status information is compared to either non-anomalous or anomalous antenna status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the antenna status information by generating a plurality of probabilistic models of the antenna status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the antenna status information prior to optimization.

Abstract: A system can determine by which path/tunnel an Internet destination can be best reached for a user with an IP address from a static BGP range. The system looks up the destination address in an egress map. This map can either specify a tunnel that should be used for encapsulation for static BGP, or (when tunnel is not present) cause the system to send out unencapsulated traffic, in which the traffic follows normal BGP routing on a border network.

Abstract: Apparatuses, systems, and techniques to place one or more objects in a location and orientation. In at least one embodiment, one or more circuits are to use one or more neural networks to cause one or more autonomous devices to place one or more objects in a location and orientation based, at least in part, on one or more images of the location and orientation.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: Apparatuses, systems, and techniques to train a machine learning model. In at least one embodiment, a first machine learning model is trained to infer a concept based on first information, training data is labeled using the first machine learning model, and a second machine learning model is trained to infer the concept using the labeled training data.

Abstract: A robotic system is provided for performing rearrangement tasks guided by a natural language instruction. The system can include a number of neural networks used to determine a selected rearrangement of the objects in accordance with the natural language instruction. A target object predictor network processes a point cloud of the scene and the natural language instruction to identify a set of query objects that are to-be-rearranged. A language conditioned prior network processes the point cloud, natural language instruction, and the set of query objects to sample a distribution of rearrangements to generate a number of sets of pose offsets for the set of query objects. A discriminator network then processes the samples to generate scores for the samples. The samples may be refined until a score for at least one of the sample generated by the discriminator network is above a threshold value.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: A system is disclosed for acquiring and managing data regarding external IP (EIP) addresses of services offered in a trusted public cloud environment. The system monitors an application program interface of a service executing in a trusted public cloud environment for occurrence of an event that is related to an EIP of the service. When an event is detected, the system extract EIP related data and metadata of the service, generates a message with the extracted EIP data, and posts the message to a central message queue. The system monitors the message queue for the presence of a new message. Upon detecting a new message, the system processes the message, extracts EIP related data. metadata, and identifies an action. A central database that stores EIP related information of services executing in the trusted public cloud environment is updated based on the identified action.

Abstract: A trigger mechanism is provided for a passive rotating jointed tubing injector having gripper blocks for moving connected, segmented oilfield tubulars axially into or out of horizontal, extended-reach oil and natural gas wells that may contain pressurized fluid or gas to complete for production, work over and service the wells, utilizing an operation commonly known as snubbing. The trigger mechanism can open the gripper blocks when a tapered upset section of increasing diameter on the tubulars is encountered that would not otherwise fully open and operate the gripper blocks.

Abstract: Apparatuses, systems, and techniques to perform a language-guided distributional tree search based at least in part on a natural language task. In at least one embodiment, a tree search is performed using one or more neural networks to determine an action to be performed by an autonomous agent.

Abstract: An apparatus for powering trucks including a power module skid and supporting structure for fitting on a truck. The skid housing hydrogen fuel cell modules, battery sub packs, cooling means and cooling management, and integrated power electronics, to provide an electrical drive train of the truck with a constant high voltage DC power supply. An integrated system using renewable energy to reduce greenhouse gases using one or more trucks, in which an integrated system includes: means for providing renewable energy; means for using the renewable energy to synthesise hydrogen; means for storing the synthesised hydrogen; The integrated system includes hybrid hydrogen power modules fitted to each truck including hydrogen fuel cell modules and battery sub packs so that the battery sub packs and the battery sub packs are recharged by the hydrogen fuel cells.

Abstract: An apparatus for powering trucks including a power module skid and supporting structure for fitting on a truck. The skid housing hydrogen fuel cell modules, battery sub packs, cooling means and cooling management, and integrated power electronics, to provide an electrical drive train of the truck with a constant high voltage DC power supply. An integrated system using renewable energy to reduce greenhouse gases using one or more trucks, in which an integrated system includes: means for providing renewable energy; means for using the renewable energy to synthesise hydrogen; means for storing the synthesised hydrogen. The integrated system includes hybrid hydrogen power modules fitted to each truck including hydrogen fuel cell modules and battery sub packs so that the battery sub packs and the battery sub packs are recharged by the hydrogen fuel cells.

Abstract: A walking system for a workover rig or completion rig mounted on a motor vehicle. The walking system includes a main platform having ramps and tracks for the motor vehicle to drive up onto and a base beam extending perpendicularly on both sides of the main platform to act as outriggers for stability. The system further includes a workstring platform for storing tubulars that make up the workstring, which is elevated above a wellhead. The main platform and base beam have walking assemblies for lifting the rig and moving it laterally so that it can be positioned over the wellhead for workover or completion operations.

Abstract: The invention includes a customized process to prepare a seasoning composition to modify a gustatory sensation experienced by an individual when a food substrate and a grape-based alcoholic beverage are consumed and the seasoning composition prepared thereby. The process includes obtaining an amount of an edible salt; selecting a grape varietal from which the grape-based alcoholic beverage is derived; determining the pairing profile of the grape-based alcoholic beverage selected from Sweet, Dry and Acidic; selecting a gustatory objective from the group consisting of a balance objective, a contrast objective, and an enhancement objective. When the objective is balance and the pairing profile is Sweet, a salty component is added to the amount of salt to form a customized seasoning composition. When the objective is balance and the pairing profile is Dry, a component selected from a salty component and an umami component is added to the amount of salt to form a customized seasoning composition.

Abstract: The invention includes a customized process to prepare a seasoning composition to modify a gustatory sensation experienced by an individual when a food substrate and a grape-based alcoholic beverage are consumed and the seasoning composition prepared thereby. The process includes obtaining an amount of an edible salt; selecting a grape varietal from which the grape-based alcoholic beverage is derived; determining the pairing profile of the grape-based alcoholic beverage selected from Sweet, Dry and Acidic; selecting a gustatory objective from the group consisting of a balance objective, a contrast objective, and an enhancement objective. When the objective is balance and the pairing profile is Sweet, a salty component is added to the amount of salt to form a customized seasoning composition. When the objective is balance and the pairing profile is Dry, a component selected from a salty component and an umami component is added to the amount of salt to form a customized seasoning composition.

Abstract: A system and method for mounting a Closed-Mouth Power Tong on a Well Servicing Rig in order is disclosed. The power tong can be operated remotely when making up or breaking out connections on oilfield tubing. The system utilizes an assembly that can lift and lower the tong to the appropriate height as required to engage the threads on the tubing. The assembly is connected to the blowout preventer or wellhead with a quick connect system that is adjustable for various angles so that the tong can be utilized in various positions to run tubing into, or out from, the well center unhindered.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: A trigger mechanism is provided for a passive rotating jointed tubing injector having gripper blocks for moving connected, segmented oilfield tubulars axially into or out of horizontal, extended-reach oil and natural gas wells that may contain pressurized fluid or gas to complete for production, work over and service the wells, utilizing an operation commonly known as snubbing. The trigger mechanism can open the gripper blocks when a tapered upset section of increasing diameter on the tubulars is encountered that would not otherwise fully open and operate the gripper blocks.