Abstract: A method in accordance with at least some embodiments of the present technology includes receiving, by a computing system operably associated with a robot, information corresponding to a position of an object in a working environment. The method further includes selecting, by the computing system and based at least partially on the information, a manipulation behavior for the object among a plurality of manipulation behaviors in a library of the computing system. The selected manipulation behavior includes repositioning the object and lifting the object after repositioning the object. At least one of repositioning the object and lifting the object is bimanual. Moreover, at least one of repositioning the object and lifting the object is nonprehensile. Finally, the method includes manipulating, by the robot, the object in accordance with the selected manipulation behavior.

Abstract: Disclosed techniques include receiving a user model as a computational graph and a list of risk metrics indicating types of risk factors to assess, and selecting at least one composable wrapper for wrapping the user model based on a risk metric(s) in the list. The techniques further include determining a set of graph-level transformations to apply to the computational graph representation that implement a risk estimate for the user model, applying the set of graph-level transformations to modify the operations performed by the user model, and generating, based on the transformed computational graph, a modified executable variant of the user model that, when executed within a machine learning framework, produces: outputs that preserve the structure and interpretation of the user model outputs; and corresponding uncertainty estimates.

Abstract: A method in accordance with at least some embodiments of the present technology includes retrieving, by a legged robot, an object from a pick target while the legged robot is in a first dynamic balancing state. The method further includes carrying, by the legged robot, the object toward a place target spaced apart from the pick target while the legged robot ambulates over a floor surface. The method further includes placing, by the legged robot, the object at the place target while the legged robot is in a second dynamic balancing state. The legged robot in one of the first and second dynamic balancing states maintains its balance while its feet are planted on the floor surface. The legged robot in the other of the first and second dynamic balancing states maintains its balance while at least one of the feet moves relative to the floor surface.

Abstract: A method in accordance with at least some embodiments of the present technology includes moving a robot toward a shelf carrying a tote. The method further includes nonprehensilely tilting the tote and nonprehensilely pulling the tote toward a body of the robot. The tilting and pulling occur while the tote is in contact with the shelf and while exerting a first compressive force on the tote via contact between opposing arms of the robot and respective side portions of the tote spaced apart from one another along a width of the tote. Next, the method includes repositioning the arms and prehensilely lifting the tote from the shelf while exerting a second, greater compressive force on the tote via contact between the arms and the respective side portions of the tote. Finally, the method includes carrying the tote away from the shelf via legged locomotion.

Abstract: Described herein are systems and methods for improving accuracy of model output generation. A method can include obtaining a risk-aware model and a user input, applying the risk-aware model to the user input, receiving, based on the applying, model output and corresponding risk values, comparing the corresponding risk values to a threshold risk value, and regenerating the user input based on the comparing. The method can also include iteratively performing the applying, receiving, comparing, and regenerating using the regenerated user input until one or more processing conditions is met. The user input can be regenerated in response to determining that the corresponding risk values are greater than the threshold risk value. The model output can include one or more sequences in a train-of-thought (TOT) of the risk-aware model.

Abstract: Methods for optimizing a user model are disclosed. In at least some instances, the methods include receiving a user model and then identifying one or more sub-optimal combinations of operations in the user model. The methods further include generating a modification (e.g., an optimal subgraph) for at least one identified sub-optimal combination of operations in the user model and replacing that identified sub-optimal combination of operations with the generated modification for that identified sub-optimal combination of operations. Still further, the method includes returning the user model with the generated modification as a transformed model. Other methods, and systems for performing any methods disclosed, are also provided.

Abstract: Methods of modifying an input, such as a prompt, for a machine learning model are disclosed. In at least some instances, the method includes transforming a received user model into a risk-aware model, applying that risk-aware model to a received input, and receiving, based on the application of the risk-aware model, output and corresponding risk values. In turn, the method includes determining whether the corresponding risk values, or an aggregate of such values, are less than a predetermined threshold level. If the values or aggregate are greater than the predetermined threshold level, then a process is performed to modify the input to minimize the corresponding risk values. The risk-aware model is iteratively applied to the modified input and the modification process continues to be performed until the corresponding risk values are less than the predetermined threshold level. Other methods, and systems for performing any methods disclosed, are also provided.

Abstract: A bone plate including a main bone plate body having two opposing curved sections adapted for a clavicle; a bendable waist portion narrower than the main body of the bone plate; and a node at each end of the main body connected to the main body by a bridge portion which is narrower than the main body, wherein the bridge includes a cut-out relief portion on a bottom side of the bone plate.

Abstract: Disclosed are techniques, and related systems, for developing and implementing a unified framework for quantifying risk in machine learning models, such as deep neural networks. The framework can be easy-to-use and flexible to apply to different types of machine learning models. The framework can be used to automatically assess different forms of risk in parallel, including but not limited to aleatoric uncertainty, epistemic uncertainty, and/or vacuitic uncertainty. To that end, the disclosed framework provides wrappers that compose different automatic risk assessment algorithms. The obtained risk estimates can be used, for example, for: providing a deeper insight into decision boundaries of neural networks; performing downstream tasks by integrating the risk estimates back into a learning lifecycle for the model to improve robustness and generalization; and/or improving safety by identifying potential model failures based on the risk values.

Abstract: A lift assembly includes an upper rail. A plurality of rail flanges extend from the upper rail. The lift assembly further includes a plurality of combustion can support assemblies spaced apart from one another. Each combustion can support assembly of the plurality of combustion can support assemblies includes a support flange slidably coupled to a rail flange of the plurality of rail flanges, an outer sleeve, and an inner sleeve assembly configured to removably couple to a combustion can of the turbomachine. Each combustion can support assembly of the plurality of combustion can support assemblies defines a cylindrical coordinate system having an axial direction, a radial direction, and a circumferential direction. Each combustion can support assembly of the plurality of support assemblies is configured to move along any of the axial direction, the radial direction, or the circumferential direction relative to the upper rail.

Abstract: A bone plate including a main bone plate body having two opposing curved sections adapted for a clavicle; a bendable waist portion narrower than the main body of the bone plate; and a node at each end of the main body connected to the main body by a bridge portion which is narrower than the main body, wherein the bridge includes a cut-out relief portion on a bottom side of the bone plate.

Abstract: A pair of plate benders is provided for bending a bone plate having a plurality of screw holes and a plurality of tubular drill guides removably preassembled into the screw holes. Each plate bender has a first end, a second end, and a handle extending between the first and second ends. The first end has a lower table on which the plate is received, an upper retaining structure which is adapted to engage the tubular drill guides, a recess defined between the lower table and upper retaining structure into which a portion of the plate is received such that the plate extends over a portion of the table and below a portion of the retaining structure. The retaining structure engages the periphery of the tubular drill guides to secure the plate relative to the bending tool.

Abstract: A bone plate including a main bone plate body having two opposing curved sections adapted for a clavicle; a bendable waist portion narrower than the main body of the bone plate; and a node at each end of the main body connected to the main body by a bridge portion which is narrower than the main body, wherein the bridge includes a cut-out relief portion on a bottom side of the bone plate.

Abstract: A pair of plate benders is provided for bending a bone plate having a plurality of screw holes and a plurality of tubular drill guides removably preassembled into the screw holes. Each plate bender has a first end, a second end, and a handle extending between the first and second ends. The first end has a lower table on which the plate is received, an upper retaining structure which is adapted to engage the tubular drill guides, a recess defined between the lower table and upper retaining structure into which a portion of the plate is received such that the plate extends over a portion of the table and below a portion of the retaining structure. The retaining structure engages the periphery of the tubular drill guides to secure the plate relative to the bending tool.

Abstract: A pair of plate benders is provided for bending a bone plate having a plurality of screw holes and a plurality of tubular drill guides removably preassembled into the screw holes. Each plate bender has a first end, a second end, and a handle extending between the first and second ends. The first end has a lower table on which the plate is received, an upper retaining structure which is adapted to engage the tubular drill guides, a recess defined between the lower table and upper retaining structure into which a portion of the plate is received such that the plate extends over a portion of the table and below a portion of the retaining structure. The retaining structure engages the periphery of the tubular drill guides to secure the plate relative to the bending tool.

Abstract: A bone plate including a main bone plate body having two opposing curved sections adapted for a clavicle; a bendable waist portion narrower than the main body of the bone plate; and a node at each end of the main body connected to the main body by a bridge portion which is narrower than the main body, wherein the bridge includes a cut-out relief portion on a bottom side of the bone plate.

Abstract: A pair of plate benders is provided for bending a bone plate having a plurality of screw holes and a plurality of tubular drill guides removably preassembled into the screw holes. Each plate bender has a first end, a second end, and a handle extending between the first and second ends. The first end has a lower table on which the plate is received, an upper retaining structure which is adapted to engage the tubular drill guides, a recess defined between the lower table and upper retaining structure into which a portion of the plate is received such that the plate extends over a portion of the table and below a portion of the retaining structure. The retaining structure engages the periphery of the tubular drill guides to secure the plate relative to the bending tool.

Abstract: A locking mechanism for securing a jumper tube to a shunt tube in a well screen assembly for use in gravel packing is disclosed. The jumper tube features a telescoping connector that extends to engage the shunt tube and a locking mechanism that extends the connector the proper distance and then locks the connector into place by engaging lugs that are connected to the jumper tube. Also disclosed is an apparatus and method for securing a connector tube to a well screen assembly using a receiver that is attached to the well screen assembly and is configured to receive a connector tube and secure the connector tube into place with screws. The receiver can be mounted to the well screen assembly via the shunt tube, a top/middle-bottom ring assembly, directly to the base pipe.