Abstract: A system for collection of rainwater in the open ocean may include: (a) one or more ocean-going vessels, wherein each ocean-going vessel is configured for collection and storage of rainwater, wherein each ocean-going vessel is configured to drift with surface ocean currents in order to navigate to one or more delivery locations, wherein each delivery location is on or near to a land mass; and (b) one or more delivery stations located at the one or more delivery locations, wherein each delivery station is configured to receive stored rainwater from one or more of the ocean-going vessels.

Abstract: A process for producing a light emitting diode device, the process including: forming a plurality of quantum dots on a surface of a layer including a first area and a second area, the forming including: exposing the first area of the surface to light having a first wavelength while exposing the first area to a quantum dot forming environment that causes the quantum dots in the first area to form at a first growth rate while the quantum dots have a dimension less than a first threshold dimension; exposing the second area of the surface to light having a second wavelength while exposing the second area to the quantum dot forming environment that causes the quantum dots in the second area to form at a third growth rate while the quantum dots have a dimension less than a second threshold dimension; and processing the layer to form the LED device.

Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for selecting a modality for interfacing between a user and a robot. In some implementations, a system determines that a particular action requires user confirmation before being performed. The system receives position data indicating a level of proximity of a user to a robot and environmental data indicating environmental conditions sensed by the robot. The system selects a particular mode for obtaining confirmation of the action from among multiple modes of interfacing with users based on one or more of the position data and the environmental data. The system provides a request confirmation of the action using the particular mode for presentation to the user.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s). In various implementations, the training is based on correction instances from multiple robots. After a revised version of a model is generated, the revised version can thereafter be utilized by one or more of the multiple robots.

Abstract: An example method includes determining a plurality of frequency ranges corresponding to a plurality of types of errors, where the plurality of frequency ranges are associated with sounds occurring during operation of a robotic device. The method also includes detecting, based on sensor data from at least one audio sensor of the robotic device, a sound during a given operation of the robotic device. The method also includes determining that a frequency of the detected sound is within a particular frequency range of the plurality of frequency ranges. Based on the frequency being within the particular frequency range, the method also includes determining a type of error of the plurality of types of errors corresponding to the particular frequency range. The method also includes providing an output signal indicating an error of the determined type.

Abstract: Methods and systems for modifying the inertial parameters used in a virtual robot model that simulates the interactions of a real-world robot with an environment to better reflect the actual inertial properties of the real-world robot. In one aspect, a method includes obtaining joint physical parameter measurements for the joints of a real-world robot, determining simulated joint physical parameter values for each of the joint physical parameter measurements, and adjusting an estimate of inertial properties of the real-world robot used by the virtual robot dynamic model to reduce a difference between the simulated joint physical parameter values and the corresponding joint physical parameter measurements.

Abstract: A light emitting device includes a substrate supporting a first light emitting element and a second light emitting element, the first light emitting element being configured to emit, in a first principal direction, light in a first wavelength band and the second light emitting element being configured to emit, in the first principal direction, light in a second wavelength band different from the first wavelength band, each light emitting element including: a light emitting diode layer, extending in a plane perpendicular to the first direction, having a thickness of 10 microns or less in the first direction and a maximum lateral dimension of 100 microns or less orthogonal to the first direction, the light emitting diode layer including a semiconductor material; and one or more layers configured to enhance an optical mode of the light emitted in the corresponding first or second wavelength band perpendicular to the plane and/or suppress an optical mode of the light emitted in the corresponding first or second w

Abstract: An electro-optic (EO) sensor and a method for detecting a local electric field strength, the EO sensor including: a first optical cavity; a gain medium within the first optical cavity; a mode locking element within the first optical cavity; and an EO material within the first optical cavity, an effective optical path length of the EO material being variable depending on the local electric field strength at the EO sensor, wherein the gain medium, the mode locking element, and the EO material are arranged in a common path of light within the first optical cavity, and wherein during operation, the EO sensor emits pulses of light at a repetition rate characteristic of an effective optical path length of the light within the first optical cavity, the effective optical path length varying depending on the electric field strength local to the EO sensor.

Abstract: Methods, systems, and apparatus for generating images that blend an appearance of a display with an environment of the display. In some aspects, output is provided from a display that occludes an object. A gaze direction is determined for an observer located within an environment of the display. An image is generated based on the determined gaze direction of the observer. The generated image is configured to blend an appearance of the display with the environment of the display. The generated image is displayed on the display directed to the observer.

Abstract: An example implementation includes a robotic system including a first wheel and a second wheel configured to rotate about a first axis. Each wheel of the first wheel and the second wheel includes a contact surface and a motor coupled to a rotatable component. Each motor is configured to rotate the rotatable component about a respective second axis. The rotatable component is frictionally engaged with the contact surface such that a rotation of the rotatable component about the respective second axis is translated to a rotation of the wheel about the first axis. The robotic system further includes a controller configured to operate the motor of the first wheel and the motor of the second wheel in order to cause the robotic system to maintain its balance and navigate within an environment based on data received from one or more sensors.

Abstract: Methods are described herein related to enabling users to purchase a product or service by providing a voice request and/or an image. An example method may involve: (a) receiving, by a hybrid response system (“HRS”), a first speech-segment message that comprises a speech segment and is associated with a user-account, (b) the HRS determining that the speech segment indicates a purchase request, (c) the HRS determining a target product/service based on at least the purchase request, (d) the HRS determining a confidence level associated with a purchase of the target product/service, (e) if the confidence level is greater than or equal to a threshold level, then the HRS sending a purchase order, via the associated user-account, for the target product or service, otherwise, the HRS sending the purchase request and the target product/service to at least one guide computing system to facilitate a response to the purchase request.

Abstract: Methods and systems for proactively preventing hazardous or other situations in a robot-cloud interaction are provided. An example method includes receiving information associated with task logs for a plurality of robotic devices. The task logs may include information associated with tasks performed by the plurality of robotic devices. The method may also include a computing system determining information associated with hazardous situations based on the information associated with the task logs. For example, the hazardous situations may comprise situations associated with failures of one or more components of the plurality of robotic devices. According to the method, information associated with a contextual situation of a first robotic device may be determined, and when the information associated with the contextual situation is consistent with information associated with the one or more hazardous situations, an alert indicating a potential failure of the first robotic device may be provided.

Abstract: Methods, systems, and apparatus for providing indications of occluded objects. In some aspects a method includes the actions of determining a position of an observer whose view of an object is obstructed by a barrier; determining a position of the object relative to the observer; generating an indication of the position of the object based at least in part on the determined position of the observer; and displaying the indication of the position of the object on a display located between the observer and the barrier.

Abstract: Methods, systems, and apparatus for receiving data that represents a portion of a property that was obtained by a robot, identifying, based at least on the data, objects that the data indicates as being located within the portion of the property, determining, based on the objects, a semantic zone type corresponding to the portion of the property, accessing a mapping hierarchy for the property, wherein the mapping hierarchy for the property specifies semantic zones of the property that have corresponding semantic zone types and are associated with locations at the property, and specifies characteristics of the semantic zones, and selecting, from among the semantic zones and based at least on the semantic zone type and the data, a particular semantic zone, and setting, as a current location of the robot at the property, a particular location at the property associated with the particular semantic zone.

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: A fish monitoring system deployed in a particular area to obtain fish images is described. Neural networks and machine-learning techniques may be implemented to periodically train fish monitoring systems and generate monitoring modes to capture high quality images of fish based on the conditions in the determined area. The camera systems may be configured according to the settings, e.g., positions, viewing angles, specified by the monitoring modes when conditions matching the monitoring modes are detected. Each monitoring mode may be associated with one or more fish activities, such as sleeping, eating, swimming alone, and one or more parameters, such as time, location, and fish type.

Abstract: Example implementations may relate to a robotic system configured to provide feedback. In particular, the robotic system may determine a model of an environment in which the robotic system is operating. Based on this model, the robotic system may then determine one or more of a state or intended operation of the robotic system. Then, based one or more of the state or the intended operation, the robotic system may select one of one or more of the following to represent one or more of the state or the intended operation: visual feedback, auditory feedback, and one or more movements. Based on the selection, the robotic system may then engage in one or more of the visual feedback, the auditory feedback, and the one or more movements.

Abstract: Example embodiments may relate to methods and systems for selecting a grasp point on an object. In particular, a robotic manipulator may identify characteristics of a physical object within a physical environment. Based on the identified characteristics, the robotic manipulator may determine potential grasp points on the physical object corresponding to points at which a gripper attached to the robotic manipulator is operable to grip the physical object. Subsequently, the robotic manipulator may determine a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object and then select a grasp point, from the potential grasp points, based on the determined motion path. After selecting the grasp point, the robotic manipulator may grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location.

Abstract: An example system includes a robotic device deployed in a warehouse environment including a plurality of inventory items. The system also includes a camera coupled to the robotic device, configured to capture image data. The system also includes a computing system configured to receive the captured image data. The computing system is configured to, based on the received image data, generate a navigation instruction for navigation of the robotic device. The computing system is also configured to analyze the received image data to detect one or more on-item visual identifiers corresponding to one or more inventory items. The computing system is further configured to, for each detected visual identifier, (i) determine a warehouse location of the corresponding inventory item, (ii) compare the determined warehouse location to an expected location, and (iii) initiate an action based on the comparison.

Abstract: A matrix computation unit includes a systolic array of cells arranged along a first and second dimension, in which the systolic array of cells includes a first multiple of cells, each cell of the first multiple of cells including: a weight register configured to store a weight input; multiple activation registers, each activation register of the multiple activation registers configured to store a corresponding activation input; multiplexer circuitry communicatively coupled to the multiple activation registers and configured to select, from the multiple activation registers, one of the activation inputs as a selected activation input; and multiplication circuitry communicatively coupled to the weight register and to the multiplexer, in which the multiplication circuitry is configured to output a product of the weight input and the selected activation input.