Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.

Abstract: The subject matter of this specification generally relates to modular vehicles including separable pod and base units. In some implementations, a computing system installed in a vehicle base identifies a vehicle pod that is detachably connected to a chassis on the vehicle base. In response to identifying that the vehicle pod is detachably connected to the chassis on the vehicle base, a communications link can be established between the computing system installed in the vehicle base and a computing system installed in the vehicle pod. Based on information obtained through the communications link, the computing system installed in the vehicle base can determine a particular configuration of the vehicle pod that is detachably connected to the chassis. The computing system can then verify that the vehicle base can safely transport the vehicle pod while the vehicle pod is detachably connected.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, can be implemented to perform certain actions. The actions can include maintaining biological data related to multiple biological systems in a first format in a data repository, receiving a first selection of a biological system of the multiple biological systems for constructing a model that simulates a behavior of the biological system, retrieving a subset of data of the biological data that is associated with the first selection of the biological system, receiving a second selection of a modeling technique of the multiple modeling techniques for constructing the model, compiling the subset of biological data into configuration data of a second format that is specific to the modeling technique and that is different from the first format, and generating the model using the modeling technique and the configuration data.

Abstract: Techniques are described herein for training a machine learning model and using the trained machine learning model to more accurately determine alignments between matching/corresponding nodes of predecessor and successor graphs representing predecessor and successor source code snippets. A method includes: obtaining a first abstract syntax tree that represents a predecessor source code snippet and a second abstract syntax tree that represents a successor source code snippet; determining a mapping across the first and second abstract syntax trees; obtaining a first control-flow graph that represents the predecessor source code snippet and a second control-flow graph that represents the successor source code snippet; aligning blocks in the first control-flow graph with blocks in the second control-flow graph; and applying the aligned blocks as inputs across a trained machine learning model to generate an alignment of nodes in the first abstract syntax tree with nodes in the second abstract syntax tree.

Abstract: A computer-implemented method for designing an image processing device includes defining a loss function within a simulation space composed of a plurality of voxels; defining an initial structure for one or more physical features of a metasurface and one or more architectural features of a neural network in the simulation space; determining, using a computer system, values for at least one structural parameter, and/or at least one functional parameter for the one or more physical features and at least one architectural parameter for the one or more architectural features, using a numerical solver to solve Maxwell's equations so that a loss determined according to the loss function is within a threshold loss; defining a final structure of the metasurface based on the values for the one or more structural parameters; and defining a final structure of the neural network based on the values for the at least one architectural parameter.

Abstract: The disclosure provides a communication system that includes sensors, a plurality of components, and processors. The sensors receive measurements related to a state of the communication system. The processors receive an indication of an amount of received power at a remote communication system and estimate a state of the plurality of components based on the received one or more measurements and the received indication. Using the indication and the estimated state, the processors determine whether the amount of received power is likely to fall below a minimum received power within a given time interval. When it is likely, the processors select an adjustment technique of a plurality of adjustment techniques for adjusting a data rate of the outbound signal and adjust a given component of the communication system using the selected adjustment technique to change the data rate of the outbound signal.

Abstract: A free-space optical communication device includes an optical fiber bundle and one or more processors. The optical fiber bundle includes a central fiber connected to a first photodetector, and a plurality of surrounding fibers, each surrounding fiber connected to a corresponding second photodetector. The one or more processors are in communication with the first photodetector and each second photodetector. The one or more processors are also configured to receive a current or voltage generated at the first photodetector and each second photodetector and to determine a pointing accuracy of a beam received at the optical fiber bundle based on the current or voltage generated at the second photodetectors.

Abstract: The present disclosure relates to leveraging explainable machine learning methods and feature importance mechanisms as a mechanism for gene discovery and furthermore leveraging the outputs of the gene discovery to recommend ideal gene expression profiles and the requisite genome edits that are conducive to a desired phenotype. Particularly, aspects of the present disclosure are directed to obtaining gene expression profiles for a set of genes measured in a tissue sample of a plant, inputting the gene expression profiles into a prediction model constructed for a task of predicting a phenotype as output data, generating, using the prediction model, the prediction of the phenotype for the plant, analyzing, by an explainable artificial intelligence system, decisions made by the prediction model to predict the phenotype, and identifying a set of candidate gene targets for the phenotype as having a largest contribution or influence on the prediction based on the analyzing.

Abstract: A method includes receiving a first depth map that includes a plurality of first pixel depths and a second depth map that includes a plurality of second pixel depths. The first depth map corresponds to a reference depth scale and the second depth map corresponds to a relative depth scale. The method includes aligning the second pixel depths with the first pixel depths. The method includes transforming the aligned region of the second pixel depths such that transformed second edge pixel depths of the aligned region are coextensive with first edge pixel depths surrounding the corresponding region of the first pixel depths. The method includes generating a third depth map. The third depth map includes a first region corresponding to the first pixel depths and a second region corresponding to the transformed and aligned region of the second pixel depths.

Abstract: A method includes receiving sensor data representing a first object in an environment and generating, based on the sensor data, a first state vector that represents physical properties of the first object. The method also includes generating, by a first machine learning model and based on the first state vector and a second state vector that represents physical properties of a second object previously observed in the environment, a metric indicating a likelihood that the first object is the same as the second object. The method further includes determining, based on the metric, to update the second state vector and updating, by a second machine learning model configured to maintain the second state vector over time and based on the first state vector, the second state vector to incorporate into the second state vector information concerning physical properties of the second object as represented in the first state vector.

Abstract: A method includes receiving, from a camera disposed on a robotic device, a two-dimensional (2D) image of a body of an actor and determining, for each respective keypoint of a first subset of a plurality of keypoints, 2D coordinates of the respective keypoint within the 2D image. The plurality of keypoints represent body locations. Each respective keypoint of the first subset is visible in the 2D image. The method also includes determining a second subset of the plurality of keypoints. Each respective keypoint of the second subset is not visible in the 2D image. The method further includes determining, by way of a machine learning model, an extent of engagement of the actor with the robotic device based on (i) the 2D coordinates of keypoints of the first subset and (ii) for each respective keypoint of the second subset, an indicator that the respective keypoint is not visible.

Abstract: The disclosure provides an apparatus that includes: a stage defining a build plane; a micro light emitting diode (?LED) array including multiple pixels and configured to emit ultraviolet (UV) light towards the build plane; a two-dimensional (2-D) voice coil manipulator mechanically coupled to the ?LED array and configured to align the pixels of the ?LED array with the build plane; and a control module programmed to cause the ?LED array to illuminate a UV curable material at the build plane to form a stack of layers of the three-dimensional object, wherein the apparatus adjusts a UV illumination pattern for the layers of the UV curable material by varying an output intensity of UV light from the pixels of the ?LED array and by varying an alignment between the ?LED array and the build plane using the 2-D voice coil manipulator.

Abstract: A method includes creating a publisher configured to send messages over a channel having a shared memory. The method includes creating at least one subscriber configured to receive the messages over the channel by sequentially referencing memory slots of the plurality of memory slots. The method includes determining that the next sequential memory slot is currently referenced by a subscriber. The method includes delaying sending the message by the publisher based on determining that the next sequential memory slot is currently referenced by the subscriber. The method includes receiving an event trigger indicative of message reading by the subscriber. The method includes, responsive to receiving the event trigger, determining that the next sequential memory slot is not currently referenced. The method includes sending the message to the next sequential memory slot based on determining that the next sequential memory slot is not currently referenced.

Abstract: Systems, methods, devices, and techniques for planning travel of an autonomous robot. A system identifies one or more obstacles that are located in proximity of at least a portion of a planned route for the autonomous robot. For each obstacle, the system: (i) determines a semantic class of the obstacle, including selecting the semantic class from a library that defines a set of multiple possible semantic classes for obstacles, and (ii) selects a planning policy for the obstacle that corresponds to the semantic class of the obstacle. The system can generate a trajectory along the at least the portion of the planned route using the selected planning policies. The robot can then initiate travel according to the trajectory.

Abstract: A reusable mechanism is disclosed for coupling two robotic appendages, such that an unintended force acting against a side of one of the appendages may decouple the appendages. The mechanism includes a revolved male dovetail mated to a revolved female dovetail. The mechanism may further include a channel within the male dovetail and a detent that inhibits rotation of the male dovetail in relation to the female dovetail.

Abstract: A flexible sensor that includes a printed circuit board (PCB), a capacitive structure on the PCB, and mechanical coupling sites. The PCB includes a slot extending from an outer edge of the PCB to an inner portion of the PCB, and the slot defines a first edge and a second edge facing the first edge. The first and second edges are separated by a gap when the PCB is in an unflexed state. The slot is configured to permit the PCB to flex so as to vary a relative position of the first edge with respect to the second edge. The capacitive structure on the PCB includes a first edge electrode on a portion of the first edge of the PCB, and a second edge electrode on a portion of a second edge of PCB. The second edge electrode is aligned with the first edge electrode across the slot.

Abstract: The disclosure provides for a method for reacquiring a communication link between a first communication device and a second communication device. The method includes using one or more processors of the first communication device to receive historical data related to the first communication device and an environment surrounding the first communication device. The one or more processors are then used to determine one or more trends in the historical data related to fading of the communication link. Based on the one or more trends, the one or more processors are used to determine a starting time and an initial search direction for a search for the communication link. The one or more processors then execute the search at the starting time from the initial search direction.

Abstract: A docking station is provided that includes at least one component configured to couple to a robot and an identification surface. The identification surface includes a first curvature that varies at a first substantially constant rate of change along a first dimension the identification includes a second curvature that varies at a second substantially constant rate of change along a second dimension. The second dimension is orthogonal to the first dimension. The identification surface includes a third curvature that varies at a third substantially constant rate of change along a third dimension. The third dimension is orthogonal to the first dimension and the second dimension.

Abstract: A computing system may obtain, for each vehicle of a plurality of vehicles located within a location area, navigation data that indicates a travel route for the vehicle. Based on the navigation data for the plurality of vehicles, the computing system determines a subset of the plurality of vehicles that are within a threshold distance of each other and have respective travel routes that at least partially overlap. The computing system selects, based on a set of selection parameters, two or more vehicles among the subset of vehicles to form a platoon of vehicles that travel in a coordinated arrangement in proximity to each other during at least a portion of the respective travel routes of the selected vehicles. The computing system can direct the selected vehicles to form the platoon of vehicles.

Abstract: The present disclosure relates to a closed loop aptamer development system that identifies one or more aptamers observed experimentally and implements machine-learning models to identify other aptamers not observed experimentally. Particularly, aspects of the present disclosure are directed to receiving a query concerning one or more targets, acquiring a library of aptamers that potential satisfy the query, identifying a first set of aptamers from the library of aptamers that substantially or completely satisfy the query, obtaining sequence data for the first set of aptamers, generating, by a prediction model, a third set of aptamers derived from the sequence data for the first set of aptamers, validating the third set of aptamers that substantially or completely satisfy the query, and upon validating the third set of aptamers and in response to the query, providing the third set of aptamers as a result to the query.