Abstract: Various embodiments include methods and interactive traffic control devices for interactively controlling traffic, which may include receiving refined location and state information associated with individual vehicles on a roadway, and determining customized dynamic traffic control instructions for a first one or more of the individual vehicles. The determined customized dynamic traffic control instructions may be based on the received refined location and state information and offer an optional route alternative to a set limited number of the individual vehicles. The first customized dynamic traffic control instructions may be transmitted by the interactive traffic control device to the first one or more of the individual vehicles.

Abstract: Various embodiments include methods and interactive traffic control devices implementing such methods to receive refined location and state information associated with individual vehicles and determine first customized dynamic traffic control instructions for a first one or more of the individual vehicles and second customized dynamic traffic control instructions for a second one or more of the individual vehicles different from the first one or more of the individual vehicles. The first customized dynamic traffic control instructions may be transmitted to the first one or more of the individual vehicles, and the second customized dynamic traffic control instructions may be transmitted to the second one or more of the individual vehicles.

Abstract: Various embodiments include processing devices and methods for managing cleaning robot behavior. In some embodiments, a processor of the cleaning robot may obtain information about one or more cleaning operations in one or more locations of a structure. The processor may analyze the information about the one or more cleaning operations in the one or more locations. The processor may determine one or more cleaning parameters for the cleaning robot based on the analysis of the information about the one or more cleaning operations. Processor may generate an instruction for the cleaning robot to schedule an operation of the cleaning robot based on the one or more cleaning parameters. The processor may execute the generated instruction to perform the operation of the cleaning robot.

Abstract: Various embodiments include processing devices and methods for managing cleaning robot behavior. In some embodiments, a processor of the cleaning robot may obtain one or more images of the location of a structure from a camera external to the cleaning robot. The processor may analyze the one or more images of the location. The processor may determine one or more mess parameters of a mess in the location based on the analysis of the one or more images of the location. The processor may generate an instruction for the cleaning robot to schedule an operation of the cleaning robot based on the one or more mess parameters. The processor may execute the generated instruction to perform the operation of the cleaning robot.

Abstract: Various embodiments include processing devices and methods for managing cleaning robot behavior. In some embodiments, a processor of the cleaning robot may obtain one or more images of the location of a structure from a camera external to the cleaning robot. The processor may analyze the one or more images of the location. The processor may determine one or more activity parameters of the location based on the analysis of the one or more images of the location. The processor may generate an instruction for the cleaning robot to schedule an operation of the cleaning robot based on the one or more activity parameters. The processor may execute the generated instruction to perform the operation of the cleaning robot.

Abstract: Various embodiments include processing devices and methods for managing cleaning robot behavior. In some embodiments, a processor of the cleaning robot may determine operational information about operations of a heating, ventilation, and air conditioning (HVAC) system for at least one room in a structure. The processor may determine a time when operation of the HVAC system will end based on the determined operational information. The processor may generate an instruction for the cleaning robot to schedule an operation of the cleaning robot for a time after operation of the HVAC system will end. The processor may execute the generated instruction to perform the operation of the cleaning robot after operation of the HVAC system ends.

Abstract: Various embodiments include processing devices and methods for managing cleaning behavior by a cleaning robot. In some embodiments, a processor of the cleaning robot may obtain user planning information and user location information from one or more information sources external to the cleaning robot. The processor may analyze the user planning information and the user location information. The processor may determine one or more cleaning parameters for the cleaning robot based on the analysis of the user planning information and the user location information. The processor may generate an instruction for the cleaning robot to schedule an operation of the cleaning robot based on the one or more cleaning parameters. The processor may execute the generated instruction to perform the operation of the cleaning robot.

Abstract: Methods, systems, and devices for robotic navigation are described. A robotic device such as a robotic vacuum or a robotic assistant may navigate a first surface. In some cases, navigating the first surface may include removing debris from the first surface. The robotic device may identify a location of a track that connects the first surface to a second surface that is vertically displaced from the first surface. The robotic device may engage the track based at least in part on the identified location. The robotic device may ascend to the second surface by activating an actuator and navigate the second surface (e.g., may remove debris from the second surface, may map the second surface, etc.).

Abstract: Aspects may augment a robotic vehicle with one or more virtual features. In some implementations, streaming video including a first-person view (FPV) of a robotic vehicle is presented on a display of a controller as the robotic vehicle traverses a course. A virtual object may be presented on the display of the vehicle controller, and a virtual contact between the robotic vehicle and the virtual object may be detected. If the virtual object is a virtual obstacle, the robotic vehicle may be penalized for making virtual contact with the virtual obstacle. If the virtual object is a virtual reward, the robotic vehicle may be rewarded for making virtual contact with the virtual reward.

Abstract: Various embodiments may include methods of using image data to estimate motion of a vehicle observed within camera images, such as images captured by a vehicle navigation system of a host vehicle. Various embodiments may include a camera capturing a sequence of images including the observed vehicle, and a processor performing image processing to identify a wheel of the observed vehicle, and determining a rate of rotation of the wheel based on changes in orientation of the wheel between at least two images within the sequence of images. The processor may further determine a speed of the observed vehicle based on the wheel's rate of rotation and diameter. The processor may further determine a direction of travel and/or turning rate of the observed vehicle by determining relative angles of wheels of the observed vehicle in at least one image.

Abstract: Aspects may provide navigation assistance to guide a robotic vehicle through a course defined by a plurality of gates each including a fiducial marker that encodes a location, an ordering, and a pose of the corresponding gate. In some implementations, an optimal trajectory may be generated through the course and used to determine whether to provide navigation assistance to the robotic vehicle. The optimal trajectory may include a reference path that extends through openings formed in center portions of the gates, and may be used to create a virtual tunnel indicating a maximum distance that the robotic vehicle may deviate from various points along the reference path. If the robotic vehicle deviates from the optimal trajectory by more than the distance while traversing the course, navigation assistance may be provided to the robotic vehicle.

Abstract: Aspects may define a race course using a plurality of gates each including a fiducial marker that encodes a location, an ordering, and a pose of the corresponding gate. Each of the gates may include an opening through which robotic vehicles participating in a race may traverse, and a flight path may be defined through the opening of the gates. Each fiducial marker may be displayed around a perimeter of the opening of a corresponding gate, and may include a unique pattern that conveys the location, ordering, and pose of the corresponding gate to video cameras provided on the robotic vehicles. A pilot may use the fiducial markers presented on the gates to navigate the robotic vehicle through the race course, for example, so that the pilot may not need to rely solely upon the first-person view provided by the streaming video transmitted from the robotic vehicle.

Abstract: Various methods for providing adaptive voxels for an aerial light show may include determining a physical location of a robotic vehicle with respect to the aerial display, determining an appropriate light emission for the aerial light show based on the physical location of the robotic vehicle with respect to the aerial display, and adjusting a light emission of a light source of the robotic vehicle accordingly.

Abstract: Embodiments include devices and methods for vehicle collision avoidance. A processor of the vehicle may receive lidar sensor data comprising one or more points including a distance and a direction from the vehicle to the one or more points. The processor may determine a velocity constraint for each of the one or more points based on the distance and direction from the vehicle to the one or more points. Based on a navigation instruction, the processor may determine one or more velocity solutions that satisfy the one or more velocity constraints. The processor may select a velocity solution from the determined one or more velocity solutions based on the navigation instruction, and may adjust a vehicle velocity based on the selected velocity solution.

Abstract: Embodiments include devices and methods for vehicle collision avoidance. A processor of the vehicle may receive sensor data comprising one or more points. The processor may determine a distance and a direction from the vehicle to the one or more points. The processor may determine a velocity constraint for each of the one or more points based on the determined distance and direction from the vehicle to the one or more points. Based on a navigation instruction, the processor may determine one or more velocity solutions that satisfy the one or more velocity constraints. The processor may select a velocity solution from the determined one or more velocity solutions based on the navigation instruction, and may adjust a vehicle velocity based on the selected velocity solution.

Abstract: A charging station for a robotic vehicle includes a base configured for use on a body of water; a docking terminal supported on the base, the docking terminal including a charger configured to charge a robotic vehicle docked on the docking terminal; and a renewable energy harvesting device coupled to the charger to provide power to the charger.

Abstract: Some embodiments include methods for customizing operation of the robotic vehicle for an operator. Such embodiments may include identifying a current operator of the robotic vehicle, configuring the robotic vehicle based on metadata associated with an operator profile for the operator, determining whether the operator has changed, and if so, identifying the new operator, deriving updated preference-based settings and performance-based settings for the new operator, and updating configurations of the robotic vehicle accordingly.

Abstract: Embodiments include methods performed by a processor of a robotic vehicle for detecting and responding to obstructions to an on-board imaging device that includes an image sensor. Various embodiments may include causing the imaging device to capture at least one image, determining whether an obstruction to the imaging device is detected based at least in part on the at least one captured image, and, in response to determining that an obstruction to the imaging device is detected, identifying an area of the image sensor corresponding to the obstruction and masking image data received from the identified area of the image sensor.

Abstract: Embodiments include devices and methods for vehicle collision avoidance. A processor of the vehicle may receive sensor data comprising one or more points. The processor may determine a distance and a direction from the vehicle to the one or more points. The processor may determine a velocity constraint for each of the one or more points based on the determined distance and direction from the vehicle to the one or more points. Based on a navigation instruction, the processor may determine one or more velocity solutions that satisfy the one or more velocity constraints. The processor may select a velocity solution from the determined one or more velocity solutions based on the navigation instruction, and may adjust a vehicle velocity based on the selected velocity solution.

Abstract: Various embodiments include dynamically controlling one or more parameters for obtaining and/or processing sensor data received from a sensor on a vehicle based on the speed of the vehicle. In some embodiments, parameters for obtaining and/or processing sensor data may be individually tuned (e.g., decreased, increased, or maintained) by leveraging differences in the level of quality, accuracy, confidence and/or other criteria in sensor data associated with particular missions/tasks performed using the sensor data. For example, the sensor data resolution required for collision avoidance may be less than the sensor data resolution required for inspection tasks, while the update rate required for inspection tasks may be less than the update rate required for collision avoidance. Parameters for obtaining and/or processing sensor data may be individually tuned based on the speed of the vehicle and/or the task or mission to improve consumption of power and/or other resources.