Abstract: The disclosure provides for a method and a system for tracking an optical communication beam based on polarization modulation of the optical communication beam. The method includes polarizing, at a first communication device, an optical communication beam in a polarization pattern. The optical communication beam carries an optical signal. The polarization pattern encodes information by varying between a first polarization direction and at least one second polarization direction. The polarized optical communication beam is then transmitted from the first communication device to a second communication device. At the second communication device, the polarized optical communication beam is processed to extract the encoded information, and the encoded information is used at the second communication device to track the optical communication beam.

Abstract: A pulley system includes a cord and a pair of stages coupled at a pivot point, the stages being independently rotatable about a stage axis. A first pulley is attached to the stages at the pivot point. Two additional pulleys are attached to one of the stages. Braking elements are attached to one of the stages and engage the cord when an uneven tension is applied.

Abstract: A method for allocating resources for a machine learning model is disclosed. A machine learning model to be executed on a special purpose machine learning model processor is received. A computational data graph is generated from the machine learning model. The computational dataflow graph represents the machine learning model which includes nodes, connector directed edges, and parameter directed edges. The operations of the computational dataflow graph is scheduled and then compiled using a deterministic instruction set architecture that specifies functionality of a special purpose machine learning model processor. An amount of resources required to execute the computational dataflow graph is determined. Resources are allocated based on the determined amounts of resources required to execute the machine learning model represented by the computational dataflow graph.

Abstract: A robotic gripping device is provided. The robotic gripping device includes a palm and a plurality of digits coupled to the palm. The robotic gripping device also includes a time-of-flight sensor arranged on the palm such that the time-of-flight sensor is configured to generate time-of-flight distance data in a direction between the plurality of digits. The robotic gripping device additionally includes an infrared camera, including an infrared illumination source, where the infrared camera is arranged on the palm such that the infrared camera is configured to generate grayscale image data in the direction between the plurality of digits.

Abstract: The disclosure provides for a communication system that includes one or more sensors and one or more processors. The one or more processors are configured to receive, during a first timeframe, a first indication of an error rate of a communication link, a second indication of an amount of received power at a remote communication system, and one or more measurements related to the state of the communication system. The one or more processors are then configured to estimate a plurality of disturbance values to the communication system according to the one or more measurements and the second indication. Each disturbance value is associated with a set of components of the communication system. The one or more processors are configured to adjust a beam divergence of a beacon beam or a communication beam transmitted from the communication system based on the plurality of disturbance values and the first indication.

Abstract: Aspects of the disclosure provide for a method of forming a communication link between two communication devices using a primary search pattern and a secondary search pattern. A misalignment between a first optical system of a first communication device and a second optical system of a second communication device is detected. The first optical system is rotated according to the primary search pattern, and the second optical system according to the secondary search pattern. At the second communication device, a set of frames is captured. Then, it is determined whether a beacon beam transmitted from the first communication device is detected in the one or more of the captured frames. When it is determined that the beacon beam is detected, the communication link is formed between the first communication device and the second communication device.

Abstract: An example system includes a vehicle, a light projector connected to the vehicle, and a control system. The control system is configured to determine a planned operating region for the vehicle within an environment. The control system is also configured to determine that the planned operating region is within a threshold distance of an object within the environment and, in response, determine a caution region to illuminate with the light projector near the object. The control system is further configured to cause the light projector to project an indication of the caution region near the object. The projected indication remains fixed in relation to the object as the vehicle moves toward the planned operating region.

Abstract: Exemplary methods and systems may help to provide content to a user and/or take to take actions on user's behalf, based on a context-specific user-network that includes surrogates for a user in a certain context. An exemplary method may involve: (a) determining a context associated with a first user-profile; (b) determining a context-specific user-network for the first user-profile in the determined context, wherein the context-specific user-network comprises one or more user-profiles that are surrogates for the first user-profile in the determined context; (c) using historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a context-based action that is appropriate in the determined context; and (d) causing a computing device associated with the first user-profile to initiate the context-based action.

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 control system may perform functions including (i) storing data indicating an association between an optical identifier and a first robot, (ii) sending, to the first robot, data encoding the optical identifier for display by the first robot, and (iii) after sending the data encoding the optical identifier, sending, to a second robot, the data indicating the association between the optical identifier and the first robot. In some examples, the first robot may receive, from the control system, data encoding a second optical identifier of the first robot so that the first robot may display the second optical identifier instead of the first optical identifier. In some examples, a first robot may capture an image of an indication of a priority status of a second robot and perform an action based on comparing a first priority status of the first robot to the second priority status of the second robot.

Abstract: Systems and methods are described include a robot and/or an associated computing system that can use various cues about an environment of the robot to apply a bias to increase the accuracy of speech transcription. In some implementations, audio data corresponding to a spoken instruction to a robot is received. Candidate transcriptions of the audio data are obtained. A respective action of the robot corresponding to each of the candidate transcriptions of the audio data is determined. One or more scores indicating characteristics of a potential outcome of performing the respective action corresponding to the candidate transcription of the audio data are determined for each of the candidate transcriptions of the audio data. A particular candidate transcription is selected from among the candidate transcriptions based at least on the one or more scores. The action determined for the particular candidate transcription is performed.

Abstract: A method for analyzing electroencephalogram (EEG) signals is disclosed. Information associated with two or more options is presented to a user. EEG signals from a sensor coupled to the user are received contemporaneously to the user receiving information associated with the two or more options. The EEG signals are processed in real time to determine which one of the options was selected by the user. In response to determining which one of the options was selected by the user, an action from one or more possible actions associated with the information presented to the user is selected. An output associated with the selected action is then generated.

Abstract: Methods and apparatus related to generating a model for an object encountered by a robot in its environment, where the object is one that the robot is unable to recognize utilizing existing models associated with the robot. The model is generated based on vision sensor data that captures the object from multiple vantages and that is captured by a vision sensor associated with the robot, such as a vision sensor coupled to the robot. The model may be provided for use by the robot in detecting the object and/or for use in estimating the pose of the object.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for generating and utilizing non-uniform volume measures for occupied voxels, where each of the occupied voxels represents an occupied point of an environment of a robot. The volume measure for each of the occupied voxels is a “padding” for the occupied voxel and indicates a volume to be utilized for that occupied voxel. The volume measures for the occupied voxels are non-uniform in that they are not all the same volume measure. During path planning, the non-uniform volume measures of the occupied voxels can be considered as “paddings” for the occupied voxels and the occupied voxels with their corresponding volume measures considered as obstacles.

Abstract: A bipartite graph structure is utilized to better store data. The bipartite graph structure may be used in a biochemical database to efficiently store a variety of molecules and processes that might occur between the molecules. Molecules are represented as molecule nodes, which may have metadata fields including a molecule name, a molecule type, a molecular formula, a sequence, a molecular charge, a set of molecular properties, and a set of component molecules. Processes operating on the molecules are represented by process nodes, which may have metadata fields including a process name, a set of process roles, a set of process properties, and a set of sub-processes. Edges, called roles, each associate a molecule node with a process node and represent the role the associated molecule plays in the associated process. The roles may contain metadata identifying the role type and the stoichiometry coefficient of the molecule in the process.

Abstract: An example method includes determining a target area of a ground plane in an environment of a mobile robotic device, where the target area of the ground plane is in front of the mobile robotic device in a direction of travel of the mobile robotic device. The method further includes receiving depth data from a depth sensor on the mobile robotic device. The method also includes identifying a portion of the depth data representative of the target area. The method additionally includes determining that the portion of the depth data lacks information representing at least one section of the target area. The method further includes providing an output signal identifying at least one zone of non-traversable space for the mobile robotic device in the environment, where the at least one zone of non-traversable space corresponds to the at least one section of the target area.

Abstract: An in-ear device includes a molding shaped to hold the in-ear device in an ear, and an audio package configured to emit sound. The audio package is structured to removably attach to the molding. An electronics package is structured to removably couple to the audio package and removably attach to the molding. The electronics package includes a controller to control the sound output from the audio package.

Abstract: Examples relate to simultaneous localization and calibration. An example implementation may involve receiving sensor data indicative of markers detected by a sensor on a vehicle located at vehicle poses within an environment, and determining a pose graph representing the vehicle poses and the markers. For instance, the pose graph may include edges associated with a cost function representing a distance measurement between matching marker detections at different vehicle poses. The distance measurement may incorporate the different vehicle poses and a sensor pose on the vehicle. The implementation may further involve determining a sensor pose transform representing the sensor pose on the vehicle that optimizes the cost function associated with the edges in the pose graph, and providing the sensor pose transform. In further examples, motion model parameters of the vehicle may be optimized as part of a graph-based system as well or instead of sensor calibration.

Abstract: A system and a method for determining local electric field strengths, the system including: a light source module configured to emit light; a plurality of electric field sensors, each sensor including a light input portion and a light output portion, each sensor including an electro-optic material arranged in a path of at least some of the received light, an optical property of the electro-optic material being variable depending on a local electric field strength at the sensor, and the electro-optic material being arranged in the sensor such that a property of the output light varies depending on the local electric field strength; a light detection module arranged to receive the output light from the sensors; and a processing module in communication with the light detection module, the processing module being programmed to determine a corresponding value for the electric field strength local to each of the sensors.

Abstract: An example method may include receiving, from a sensor on a vehicle, an initial plurality of sensor data points representing a position of a face of a pallet. The vehicle may include tines configured to engage the pallet. A baseline geometric representation of the face of the pallet may be determined based on the initial plurality of sensor data points. The vehicle may be caused to reposition the tines relative to the pallet. A subsequent plurality of sensor data points representing the position of the face of the pallet after repositioning the tines may be received from the sensor. An updated geometric representation of the face of the pallet may be determined based on the subsequent sensor data points. It may be determined that the updated geometric representation deviates from the baseline geometric representation by more than a threshold value and, in response, motion of the vehicle may be adjusted.