Abstract: A method comprises detecting one or more agent objects in a space around an ego object using image data captured by a camera of the ego object; storing a hierarchical nodal graph comprising a goal layer comprising one or more goal nodes and a plurality of interaction layers of interaction nodes subsequent to the goal layer; adding an interaction node to an interaction layer of interaction nodes of the plurality of interaction layers; determining a trajectory score for each of a plurality of trajectories based on one or more node scores of one or more nodes corresponding to the trajectory within the hierarchical nodal graph; and selecting a trajectory of the plurality of trajectories for the ego object based on the trajectory score for the trajectory.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: A replacement heart valve device is disclosed. In some embodiments, the device includes a frame coupled to one or more leaflets that are moveable between open and closed configurations. In some embodiments, the frame comprises at least two frame sections that join at a pair of commissural posts. In some embodiments, the device may be geometrically accommodating to adapt to different vasculature shapes and sizes and/or to be able to change size while implanted within a growing patient.

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

Abstract: A replacement heart valve device is disclosed. In some embodiments, the device includes a frame coupled to one or more leaflets that are moveable between open and closed configurations. In some embodiments, the frame comprises at least two frame sections that join at a pair of commissural posts. In some embodiments, the device may be geometrically accommodating to adapt to different vasculature shapes and sizes and/or to be able to change size while implanted within a growing patient.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: Disclosed herein are systems and methods for managing exceptions to orders collected by autonomous vehicles. The exemplary systems may be configured to receive an indication of an exception that at least one item for an order cannot be collected with a first autonomous vehicle carrying a container associated with the order and determine a reconfigured path for the first vehicle responsive to receiving the indication of the exception. The reconfigured path may include a stop at a storage location configured to store containers associated with the exception. The systems may be configured to receive an indication that the container was removed from the first vehicle and deposited at the storage location, transmit an instruction to a second autonomous vehicle to collect the at least one item for the order, and receive an indication that the at least one item has been matched with the container deposited at the storage location.

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

Abstract: Disclosed herein are systems and methods for managing exceptions to orders collected by autonomous vehicles. The exemplary systems may be configured to receive an indication of an exception that at least one item for an order cannot be collected with a first autonomous vehicle carrying a container associated with the order and determine a reconfigured path for the first vehicle responsive to receiving the indication of the exception. The reconfigured path may include a stop at a storage location configured to store containers associated with the exception. The systems may be configured to receive an indication that the container was removed from the first vehicle and deposited at the storage location, transmit an instruction to a second autonomous vehicle to collect the at least one item for the order, and receive an indication that the at least one item has been matched with the container deposited at the storage location.

Abstract: A leading edge structure for providing an aerodynamic surface of an aircraft is disclosed having a skin structure, the skin structure providing an outer aerodynamic surface and an inner surface, both surfaces extending in a chordwise and spanwise direction of the structure, and a plurality of structural members, each structural member being connected to the inner surface of the skin structure and extending in the chordwise direction along the inner surface, wherein the structural members are integrally formed with the inner surface of the skin structure. The disclosure is also related to an aircraft wing, aircraft tailplane, wing box structure, wing or wing structure and an aircraft including the leading edge structure.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

Abstract: A replacement heart valve device is disclosed. In some embodiments, the device includes a frame coupled to one or more leaflets that are moveable between open and closed configurations. In some embodiments, the frame comprises at least two frame sections that join at a pair of commissural posts. In some embodiments, the device may be geometrically accommodating to adapt to different vasculature shapes and sizes and/or to be able to change size while implanted within a growing patient.

Abstract: A replacement heart valve device is disclosed. In some embodiments, the device includes a frame coupled to one or more leaflets that are moveable between open and closed configurations. In some embodiments, the frame comprises at least two frame sections that join at a pair of commissural posts. In some embodiments, the device may be geometrically accommodating to adapt to different vasculature shapes and sizes and/or to be able to change size while implanted within a growing patient.

Abstract: A replacement heart valve device is disclosed. In some embodiments, the device includes a frame coupled to one or more leaflets that are moveable between open and closed configurations. In some embodiments, the frame comprises at least two frame sections that join at a pair of commissural posts. In some embodiments, the device may be geometrically accommodating to adapt to different vasculature shapes and sizes and/or to be able to change size while implanted within a growing patient.

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.