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 and apparatus related to robot collision avoidance. One method may include: receiving robot instructions to be performed by a robot; at each of a plurality of control cycles of processor(s) of the robot: receiving trajectories to be implemented by actuators of the robot, wherein the trajectories define motion states for the actuators of the robot during the control cycle or a next control cycle, and wherein the trajectories are generated based on the robot instructions; determining, based on a current motion state of the actuators and the trajectories to be implemented, whether implementation of the trajectories by the actuators prevents any collision avoidance trajectory from being achieved; and selectively providing the trajectories or collision avoidance trajectories for operating the actuators of the robot during the control cycle or the next control cycle depending on a result of the determining.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for generating and using a spatio-temporal model that defines pose values for a plurality of objects in an environment and corresponding times associated with the pose values. Some implementations relate to using observations for one or more robots in an environment to generate a spatio-temporal model that defines pose values and corresponding times for multiple objects in the environment. In some of those implementations, the model is generated based on uncertainty measures associated with the pose values. Some implementations relate to utilizing a generated spatio-temporal model to determine the pose for each of one or more objects an environment at a target time. The pose for an object at a target time is determined based on one or more pose values for the object selected based on a corresponding measurement time, uncertainty measure, and/or source associated with the pose values.

Abstract: Example implementations relate to a solar panel system including solar cells and an inverter configured to receive electrical energy generated by solar cells and to convert the electrical energy to an electrical signal having an oscillation frequency. The system also include a transmit resonator coupled to the inverter and configured to resonate at the oscillation frequency. Moreover, the transmit resonator may be coupled via a wireless resonant coupling link to a receive resonator that is also configured to resonate at the oscillation frequency. Further, the system may also include a controller configured to determine for the system a mode of operation from among the following modes: (i) a common mode, (ii) a differential mode, and (iii) an inductive mode. And the controller is then configured to instruct the transmit resonator to provide via the wireless resonant coupling link electrical power according to the determined mode of operation.

Abstract: The present disclosure provides a method operable in a balloon network. The method can include determining that a balloon is at a location associated with a first legally-defined geographic area, wherein an area profile identifies a list of geographically-prohibited data that is restricted from being cached in the first legally-defined geographic area. The method can also include receiving first data. The method can also include using the list of geographically-prohibited data to determine whether or not the first data is geographically-prohibited data. If the first data is geographically-prohibited data, then the method can further include refraining from storing the first data in data storage at the first balloon.

Abstract: An example fabrication system includes a light source, a resin container, and a base plate on which resin is cured using the light source so as to build up an object one layer at a time. The disclosed base plate includes a build surface and an anchor channel that extends into the base plate from the build surface. The anchor channel is a recess in the base plate configured to have a narrow width that is closer to an opening to the build surface than a broad width. The base plate can also have a light source that emits light into the anchor channel to cure resin within the anchor channel. Resin anchors cured within the anchor channel to conform to the anchor channel resist being extracted, and an object formed on the build surface remains anchored during fabrication via adhesion to the resin anchors.

Abstract: A shaft may be rotated, where the shaft includes an encoder with a first, second, and third logical track, where the first and second logical tracks include bit patterns that are readable to be 90 degrees out of phase with one another, and where the third logical track includes a sequence of n numbers, each number being represented by m bits, where n is greater than 1. While moving the shaft, a number of the sequence from the third logical track and an extent of bits from the first or second logical track may be read. An orientation of the shaft may then be determined based on the number and the extent of bits. The orientation may be a linear position of a linear encoder or an angular position of a rotary encoder.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for creating, storing, and/or offloading tagged robot sensor data. In various implementations, a first plurality of sensor data points that are sampled by one or more sensors associated with a robot and that share a first attribute may be identified. Each of the first plurality of sensor data points may be tagged with a first tag, which may be indicative of the first attribute. A context in which a robot is operating may be identified. A first transport rule that governs how sensor data points tagged with the first tag are treated when the robot operates in the context may then be identified. At least a subset of the first plurality of tagged sensor data points may then be offloaded from the robot and/or stored locally on the robot pursuant to the first transport rule.

Abstract: A method includes receiving a first optical signal at a first communication terminal from a second communication terminal through a free space optical link and determining a receiving power for the optical link based on the first optical signal. The method further includes adjusting an output amplification at the first communication terminal based on the receiving power for the optical link. The output amplification is adjusted to provide a second optical signal with a minimum transmission power for maintaining the optical link. The method transmits the second optical signal from the first communication terminal to the second communication terminal through the optical link.

Abstract: An example method involves receiving, from at least one camera located in an environment, a plurality of images captured during a first time interval. The method also involves selecting one or more of the plurality of images having a movable platform supporting one or more objects. The method further involves generating a three-dimensional model of the movable platform supporting the one or more objects. The method yet further involves updating the three-dimensional model based on one or more images captured during a second time interval. The method still further involves presenting the three-dimensional model via a display of a user interface, and providing an option to view a history of the three-dimensional model such that the three-dimensional model remains in a fixed position on the display during a viewing of the history.

Abstract: A color shifting illuminator includes a first luminescent material that absorbs first incident photons having an energy greater than or equal to a first threshold energy, and emits first photons with less energy than the first incident photons. The color shifting illuminator also includes a second luminescent material that absorbs second incident photons having an energy greater than or equal to a second threshold energy, and emits second photons with less energy than the second incident photons and less energy than the first photons. The first luminescent material and the second luminescent material are included in a waveguide, and the waveguide exhibits total internal reflection for the first photons and the second photons satisfying conditions for total internal reflection. An extraction region is coupled to the waveguide to emit the first photons and the second photons.

Abstract: A mobile telepresence system may include a frame, a propulsion system operably coupled to the frame to propel the frame through a designated space, a screen movably coupled to the frame, and an image output device coupled to the frame. The frame may include a central body defining a longitudinal axis of the frame, a first arm at a first end portion of the central body, and a second arm at a second end portion of the central body, opposite the first end portion of the central body. The propulsion system may include rotors at opposite end portions of the first and second arms which propel the frame in response to an external command. The image output device may project an image onto the screen in response to an external command.

Abstract: Systems and methods related to roadmaps for mobile robotic devices are provided. A computing device can receive a roadmap. The roadmap can include an intersection between first and second edges. The computing device can determine a transition curve between the first and second edges and includes first, second, and third curve segments. The first and second curve segments can connect at a first curve junction point. The second and third curve segments can connect at a second curve junction point. The first and third curve segments each include a segment of an Euler spiral and the second curve segment can be a circular curve segment having a fixed radius. The computing device can update the roadmap by replacing the intersection between the first and second edges with the transition curve. The computing device can provide the updated roadmap.

Abstract: An example system may include a vehicle, a sensor, and a control system that may determine a target location for an object carried by the vehicle. The control system may also determine a plurality of points defining a boundary of a volume to be occupied by the object at the target location. The plurality of points may be scannable in a sequence by the sensor to scan the volume. The control system may additionally determine a respective field of visibility to each respective point. Further, the control system may determine a path for the vehicle to follow to the target location. The respective field of visibility may intersect with at least a respective portion of the determined path such that each respective point is observable by the sensor along at least the respective portion of the determined path as the vehicle moves along the determined path to the target location.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for detecting a geometric change in a robot's configuration and taking responsive action in instances where the geometric change is likely to impact operation of the robot. In various implementations, a geometric model of a robot in a selected pose may be obtained. Image data of the actual robot in the selected pose may also be obtained. The image data may be compared to the geometric model to detect a geometric difference between the geometric model and the actual robot. Output may be provided that is indicative of the geometric difference between the geometric model and the actual robot.

Abstract: Embodiments described herein may help to provide medical support via a fleet of unmanned aerial vehicles (UAVs). An illustrative UAV may include a housing, a payload, a line-deployment mechanism coupled to the housing and a line, and a payload-release mechanism that couples the line to the payload, wherein the payload-release mechanism is configured to release the payload from the line. The UAV may further include a control system configured to determine that the UAV is located at or near a delivery location and responsively: operate the line-deployment mechanism according to a variable deployment-rate profile to lower the payload to or near to the ground, determine that the payload is touching or is within a threshold distance from the ground, and responsively operate the payload-release mechanism to release the payload from the line.

Abstract: An example method is carried out in a warehouse environment having a plurality of inventory items located therein, each having a corresponding on-item identifier. The method involves determining a target inventory item having a target on-item identifier. The method also involves determining that a first inventory item having a first on-item identifier is loaded onto a first robotic device. The method further involves transmitting a request to verify the first on-item identifier. The method still further involves receiving data captured by a sensor of the second robotic device. The method yet further involves (i) analyzing the received data to determine the first on-item identifier, (ii) comparing the first on-item identifier and the target on-item identifier, and (iii) responsive to comparing the first on-item identifier and the target on-item identifier, performing an action.

Abstract: An autonomous submersible structure includes a cage for protecting cargo contained within a volume of the cage, two or more independently operated propellers, and a raised platform. The raised platform includes a plurality of sensors and computers that detect at least one of: water quality, water pressure, or objects in the vicinity of the cage. The raised platform includes a navigating system that controls a direction of travel of the cage based on feedback provided by the plurality of sensors and computers, and a power generator that provides power to the sensors, the navigating system, and the feeding mechanism. The autonomous submersible structure includes a ballast for counterbalancing the weight of the raised platform, wherein the navigating system controls the two or more independently operated propellers to alter the direction of travel of the cage, and wherein the raised platform is environmentally sealed and a portion of the raised platform is positioned above water level.