Abstract: Methods, apparatus, systems, and computer readable media are provided for generating a trajectory for a robot to enable a reference point of the robot to reach a target waypoint. A real time trajectory generator is utilized to generate a first segment of a trajectory toward a target waypoint. While the robot is traversing the first segment of the trajectory, a trajectory optimizer is utilized to generate a second segment of the trajectory from an “end point” of the first segment (an actual end of the first segment or a defined “hand off” point) until the target waypoint is reached (or until an intermediate waypoint is reached). The trajectory optimizer may utilize anticipated motion states of one or more actuators of the robot at the end point of the first segment in generating the second segment.

Abstract: Aspects of the disclosure relate to techniques for manufacturing a balloon envelope. In one example, a first sheet of material for a first gore of the balloon envelope is provided. Lap seal material is arranged at least partially on the first sheet of material. A first heat seal is created between the lap seal material and the first sheet of material. A second sheet of material for a second gore of the balloon envelope is arranged over the first heat seal. A second heat seal is created between the lap seal material and the second sheet of material such that the lap seal material is configured to provide additional structural support to the balloon envelope.

Abstract: Embodiments relate to a client-facing application for interacting with a transport service that transports items via unmanned aerial vehicles (UAVs). An example graphic interface may allow a user to order items to specific delivery areas associated with their larger delivery location, and may dynamically provide status updates and other functionality during the process of fulfilling a UAV transport request.

Abstract: A light concentrator includes a luminescent concentrator and a gain medium. The luminescent concentrator includes a semiconductor material and the semiconductor material absorbs first photons. The first photons have energy greater than or equal to a threshold energy, and the semiconductor material emits second photons through a spontaneous emission process where the second photons have less energy than the first photons. The gain medium is optically coupled to the luminescent concentrator to receive the second photons. The gain medium absorbs the second photons, and in response to absorbing the second photons, the gain medium emits third photons through a stimulated emission process. The third photons have less energy than the second photons.

Abstract: Methods and systems for using projected patterns to facilitate mapping of an environment are provided herein. A computing system may cause fixedly-posed projectors to each provide, onto a respective area of the environment, a predetermined respective distinct pattern. The system may determine respective poses of the projectors, and further determine a map of the environment that identifies, for each distinct pattern, respective locations on one or more surfaces in the environment on which the distinct pattern is detectable. Based on sensor data the system may identify a portion of a particular distinct pattern in the environment. The system may use the map and the respective pose of a particular projector that is providing the particular pattern to make a determination that the portion is located at a new, different location compared to the map. The system may then transmit an output signal indicating the determination.

Abstract: Methods and systems for dynamically maintaining a map of robotic devices in an environment are provided herein. A map of robotic devices may be determined, where the map includes predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform a task. During a performance of the task by the one or more robotic devices, task progress data may be received from the robotic devices, indicative of which of the task phases have been performed. Based on the data, the map may be updated to include a modification to the predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform at least one other task in accordance with the updated map.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for delegating object type and/or pose detection to a plurality of “targeted object recognition modules.” In some implementations, a method may be provided that includes: operating an object recognition client to facilitate object recognition for a robot; receiving, by the object recognition client, sensor data indicative of an observed object in an environment; providing, by the object recognition client, to each of a plurality of remotely-hosted targeted object recognition modules, data indicative of the observed object; receiving, by the object recognition client, from one or more of the plurality of targeted object recognition modules, one or more inferences about an object type or pose of the observed object; and determining, by the object recognition client, information about the observed object, such as its object type and/or pose, based on the one or more inferences.

Abstract: Embodiments are described for determining wind by an airborne aerial vehicle without reliance on direct measurements of airspeed by the vehicle. Instead, wind may be computationally estimated using disclosed techniques for utilizing measurements of only ground-speed and heading, or only measurements of forces experienced by the airborne aerial vehicle during flight. In one technique, samples of ground-speed measurements and corresponding heading measurements of an airborne vehicle are used in a mathematical optimization of a wind-driven hypothesis of deviations between the two types of measurement at each of multiple sampling times. In another technique, an aerodynamic model of an aerial vehicle can be used to adjust parameters of a wind hypothesis in order to achieve a best-fit between predicted and measured forces on the aerial vehicle during flight.

Abstract: Some aspects are related to methods and apparatus that enable authorization of one or more functionalities of a robot based on a user physically manipulating the robot. For example, an authorization for a robot may include one or more authorization parameters associated with physical manipulation of the robot and sensor data generated in response to physical manipulation of the robot by a user may be utilized to determine if the physical manipulation conforms to the authorization parameters. If conformance is determined, one or more functionalities of the robot may be activated. Some implementations additionally and/or alternatively relate to methods and apparatus for adapting one or more physical control parameters for a robot based on preferences of a user of the robot, such as a user that is currently authorized for the robot.

Abstract: A block-and-tackle transmission includes a timing belt input pinion, a timing belt, two or more shuttles, an output cable, and an output hub. The timing belt input pinion is for receiving input power. The timing belt is driven by the input pinion. The timing belt causes two shuttles of the two or more shuttles to move in opposing directions. Opposing ends of the output cable are pulled by two of the two or more shuttles. The output cable causes the output hub to transmit output power.

Abstract: A robotic gripping device is provided. The device includes a finger having a worm gear coupled to its base end. The device also includes an actuator having a motor and a shaft, wherein the shaft is configured to rotate a worm coupled to the worm gear, and the actuator is mounted on a carriage such that the actuator is configured to slide along an axis. The device also includes a spring having first and second ends, wherein the first end is coupled to the motor and the second end is fixed. Further, the actuator is configured to (i) rotate the shaft relative to the motor by a first amount to move the finger toward an object, and (ii) when the finger is in contact with the object and is prevented from further movement, further rotate the shaft relative to the motor to slide the actuator along the axis.

Abstract: An example robotic chassis may include a frame including a first side member and a second side member connected by a transverse member near respective first ends of first side member and the second side member. The robotic chassis may also include a rigid case having a mounting point for a tablet computer. The rigid case may be rotatably coupled between the side members near respective second ends of the side members. The robotic chassis may further include a first arm and a second arm having respective distal ends and respective proximal ends. Respective proximal ends of the first arm and the second arm may be rotatably coupled to the frame near opposite respective first ends of the first side member and the second side member. In addition, the robotic chassis may include a plurality of wheels rotatably coupled to the frame.

Abstract: Systems and methods are disclosed for determining tool offset data for a tool attached to a robot at an attachment point. In an embodiment, a method includes controlling the robot to contact a reference object with the tool. The reference object is a rigid object with a known location. A force feedback sensor of the robot may indicates when the tool has contacted the reference object. Once contact is made, data indicating robot position during tool contact is received. Additionally, the robot may temporarily stops movement of the tool to prevent damage to the tool or the reference object. Next, tool offset data s determined based on the position of the reference object relative to the robot and the received robot position data. The tool offset data describes the distance between at least one point on the tool and the attachment point.

Abstract: A communication system includes a transparent refractive optical wedge, a steerable mirror, a position feedback device, and a transceiver. The transparent refractive optical wedge has first and second faces angled with respect to each other and receives first and second optical signals through both the first and second faces. The first and second optical signals travel along parallel or common paths through the first face and diverge at a deflection angle with respect to each other through the second face. The steerable mirror is in optical communication with the first face of the optical wedge, the position feedback device, and the transceiver. The position feedback device adjusts a position of the steerable mirror to maintain the alignment of the reflected signal with the position feedback device. The transceiver has an optical transmitter transmitting one of the optical signals and an optical receiver receiving the other optical signal.

Abstract: A device is provided that includes a light-sensing layer including photodetectors, a light guide arranged to direct light beams towards a document area, and an angle-selective layer arranged to filter light beams reflected from the document area based on respective angles of incidence of the reflected light beams. The device also includes a controller configured to: operate the light guide to emit light, such that a plurality of light beams is directed towards the document area, where a portion of the light beams is reflected off of the document area and filtered by the angle-selective layer to direct a subset of the reflected light beams to the light-sensing layer. The controller is also configured to receive data indicative of the subset of light beams, generate an image of a document in the document area, detect text in the image, translate the text, and display the translated text on a display.

Abstract: Example implementations may relate to a cloud service that stores a detection metric corresponding to a maintenance request for a particular component. In particular, the cloud may receive sensor data from various robotic systems each having the particular component. The cloud may then determine, based on the sensor data, performance data for the particular component over time at the various robotic systems. The cloud may also determine various maintenance events for the particular component. Based on the performance data, the cloud may determine that at least one maintenance event occurs at other metrics that are different from the detection metric. Responsively, the cloud may adjust the detection metric based on a difference between the detection metric and the other metrics. The cloud may then detect operation of a particular robotic system at the adjusted detection metric and may responsively request maintenance for the particular component at the particular robotic system.

Abstract: A robotic gripping device is provided. The robotic gripping device includes two opposable fingers and an actuator having a motor and a shaft, wherein the shaft is coupled to a first finger. The robotic gripping device also includes a torsion spring surrounding the actuator, the torsion spring having first and second ends, wherein the first end is coupled to the motor of the actuator and the second end is coupled to a second finger. Further, the actuator is configured to rotate the shaft relative to the motor by a first amount to move the two opposable fingers toward each other to contact the object. The actuator is also configured to further rotate the shaft relative to the motor to wind up the torsion spring when the two opposable fingers are both in contact with the object and the object prevents the fingers from further movement toward each other.

Abstract: The present disclosure provides pumped thermal energy storage systems that can be used to store electrical energy. A pumped thermal energy storage system of the present disclosure can store energy by operating as a heat pump or refrigerator, whereby net work input can be used to transfer heat from the cold side to the hot side. A working fluid of the system is capable of efficient heat exchange with heat storage fluids on a hot side of the system and on a cold side of the system. The system can extract energy by operating as a heat engine transferring heat from the hot side to the cold side, which can result in net work output. Systems of the present disclosure can employ solar heating for improved storage efficiency.

Abstract: An example implementation includes operating a robotic system in an environment. The implementation also includes detecting, using one or more sensors of the robotic system, a surface marker at a first location in the environment. The implementation also includes determining that the detected surface marker indicates the presence of an object having a first surface attribute at the first location, wherein the first surface attribute is one of a plurality of predefined surface attributes. The implementation also includes determining one or more tasks that correspond to the first surface attribute in response to determining that the surface marker indicates the object having the first surface attribute. The implementation also includes causing the robotic system to perform the one or more tasks with respect to the object.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for synthetic imaging. In one aspect, a method includes receiving from each digital camera respective imaging data, each digital camera having a viewpoint that is different from the viewpoints of each other digital camera and having a field of view that is overlapping with at least one other digital camera; for a synthetic viewpoint that is a viewpoint that is within a geometry defined by the viewpoints of the digital cameras, selecting respective imaging data that each has a field of view that overlaps a field of view of the synthetic viewpoint and generating, from the selected respective imaging data, synthetic imaging data that depicts an image captured from a virtual camera positioned at the synthetic viewpoint.