Abstract: The present disclosure provides systems and methods that leverage machine-learned models in conjunction with user-associated data and disease prevalence mapping to predict disease infections with improved user privacy. In one example, a computer-implemented method can include obtaining, by a user computing device associated with a user, a machine-learned prediction model configured to predict a probability that the user may be infected with a disease based at least in part on user-associated data associated with the user. The method can further include receiving, by the user computing device, the user-associated data associated with the user. The method can further include providing, by the user computing device, the user-associated data as input to the machine-learned prediction model, the machine-learned prediction model being implemented on the user computing device.

Abstract: Example implementations may relate to selection between a first mode and a second mode. The first mode may involve (i) directing an aerial vehicle (e.g., in an aerial network including a plurality of aerial vehicles) to navigate to each of a plurality of altitudes and (ii) determining respective wind-related data at each respective altitude. Whereas, the second mode may involve (i) selecting at least one altitude based on the determined wind-related data and (ii) directing the aerial vehicle to reposition to the at least one selected altitude. As such, a control system may determine flight data for the aerial vehicle. Based on the flight data, the control system may make a selection between the first mode and the second mode. And based on the selection, the control system may then operate the aerial vehicle according to the first mode or may operate the aerial vehicle according to the second mode.

Abstract: Example implementations may relate to selection between a first mode and a second mode. The first mode may involve (i) directing an aerial vehicle (e.g., in an aerial network including a plurality of aerial vehicles) to navigate to each of a plurality of altitudes and (ii) determining respective wind-related data at each respective altitude. Whereas, the second mode may involve (i) selecting at least one altitude based on the determined wind-related data and (ii) directing the aerial vehicle to reposition to the at least one selected altitude. As such, a control system may determine flight data for the aerial vehicle. Based on the flight data, the control system may make a selection between the first mode and the second mode. And based on the selection, the control system may then operate the aerial vehicle according to the first mode or may operate the aerial vehicle according to the second mode.

Abstract: Example methods and systems for determining when to launch vehicles into a fleet of autonomous vehicles are described. A method comprises receiving a sequence of coverage requirements for a region over a period of time. The region may be characterized by landmarks and the period of time can be divided into time intervals. The method also includes defining a landmark as a launch site representative of a landmark at which a given vehicle can be added to a plurality of operating vehicles, and determining for a respective landmark, estimated landmarks that can be reached by a vehicle starting from the respective landmark by an end of a time interval. The method also includes based on the sequence of coverage requirements and the estimated landmarks, determining a given launch site and corresponding time interval at which to add the given vehicle to the plurality of operating vehicles.

Abstract: Example implementations may relate to selection between a first mode and a second mode. The first mode may involve (i) directing an aerial vehicle (e.g., in an aerial network including a plurality of aerial vehicles) to navigate to each of a plurality of altitudes and (ii) determining respective wind-related data at each respective altitude. Whereas, the second mode may involve (i) selecting at least one altitude based on the determined wind-related data and (ii) directing the aerial vehicle to reposition to the at least one selected altitude. As such, a control system may determine flight data for the aerial vehicle. Based on the flight data, the control system may make a selection between the first mode and the second mode. And based on the selection, the control system may then operate the aerial vehicle according to the first mode or may operate the aerial vehicle according to the second mode.

Abstract: Example implementations may relate to selection between a first mode and a second mode. The first mode may involve (i) directing an aerial vehicle (e.g., in an aerial network including a plurality of aerial vehicles) to navigate to each of a plurality of altitudes and (ii) determining respective wind-related data at each respective altitude. Whereas, the second mode may involve (i) selecting at least one altitude based on the determined wind-related data and (ii) directing the aerial vehicle to reposition to the at least one selected altitude. As such, a control system may determine flight data for the aerial vehicle. Based on the flight data, the control system may make a selection between the first mode and the second mode. And based on the selection, the control system may then operate the aerial vehicle according to the first mode or may operate the aerial vehicle according to the second mode.

Abstract: Example methods and systems for determining when to decommission vehicles from a fleet of autonomous vehicles are described. One method includes receiving information indicating a sequence of coverage requirements for a region over a period of time, and the region is characterized by landmarks and the period of time is divided into time intervals. Landmarks may be defined as a decommissioning site representative of a location at which a given vehicle can be taken out of service, and the method includes determining estimated landmarks that can be reached by one or more vehicles starting from a respective landmark by an end of a respective time interval, and based on the sequence of coverage requirements, determining which vehicles from among the vehicles that can reach the one or more landmarks defined as the decommissioning site to take out of service.

Abstract: An example computer-implemented method involves determining that an aerostat is located within a first atmospheric layer. A first wind-velocity measure is indicative of wind velocity in the first atmospheric layer. The method also involves determining an altitude of an atmospheric layer boundary between the first atmospheric layer and a second atmospheric layer. A second wind-velocity measure is indicative of wind velocity in the second atmospheric layer, and the second wind-velocity measure differs from the first wind-velocity measure by at least a threshold amount. The method further involves determining a desired location for the aerostat, and during at least a portion of a flight towards the desired location, causing the aerostat to traverse back and forth across the atmospheric layer boundary while remaining within a predetermined vertical distance from the atmospheric layer boundary in order to achieve a desired horizontal trajectory.

Abstract: Methods and systems for determining control policies for a fleet of vehicles are provided. In one example, a method is provided that comprises receiving a sequence of coverage requirements for a region and an associated period of time, and receiving an initial location of one or more vehicles of a fleet of vehicles. The method may further include determining a control policy for each of the one or more vehicles. Additionally, based on the determined control policies and the initial locations, one or more estimated distributions of the fleet of vehicles at respective phases within the period of time may be determined. According to the method, a score associated with the control policies may be determined based on a comparison between the estimated distributions and corresponding desired distributions of the sequence of coverage requirements. In some examples, the control policies may also be revised using an optimization technique.

Abstract: This disclosure relates to the use of an optimal altitude controller for super pressure aerostatic balloon in connection with a balloon network. The aerostatic balloon includes a bladder containing a gas that is lighter than the air present in the environment of the balloon. Additionally, the aerostatic balloon includes an envelope filled with air. A mass-changing unit configured to selectively add or remove air may control the amount of air in the envelope. Further, the balloon has a communication module configured to transmit data relating to a current balloon state, and receives data relating to a desired balloon state. Additionally, the balloon includes a processor configured to control the mass-changing unit based on the desired balloon state. The mass-changing unit of the aerostatic balloon may be powered by a renewable energy source, such as solar power. The mass-changing unit adds or removes air with an impeller.

Abstract: This disclosure relates to the use of an optimal altitude controller for super pressure aerostatic balloon in connection with a balloon network. The aerostatic balloon includes a bladder containing a gas that is lighter than the air present in the environment of the balloon. Additionally, the aerostatic balloon includes an envelope filled with air. A mass-changing unit configured to selectively add or remove air may control the amount of air in the envelope. Further, the balloon has a communication module configured to transmit data relating to a current balloon state, and receives data relating to a desired balloon state. Additionally, the balloon includes a processor configured to control the mass-changing unit based on the desired balloon state. The mass-changing unit of the aerostatic balloon may be powered by a renewable energy source, such as solar power. The mass-changing unit adds or removes air with an impeller.

Abstract: Methods and systems for determining trajectories for vehicles of a fleet of vehicles are provided. In one example, a method comprises receiving an initial location of one or more vehicles, and receiving a sequence of coverage requirements for a region and an associated period of time. The region may be divided into a plurality of landmarks and the period of time may be divided into a plurality of phases. The method also comprises determining for each of one or more phases and at least one respective landmark, a set of starting landmarks from which a vehicle could reach the respective landmark during the phase. The method further comprises determining which respective landmark that the vehicle should travel to during the one or more phases based on the sequence of coverage requirements and the set of starting landmarks for the one or more phases and the at least one respective landmark.

Abstract: Methods and systems for reverse-iterating a backward planner determining trajectories for vehicles of a fleet of vehicles are provided. In one example an iterator configured for recursively determining the contingency tables at successive time steps in a computational iteration order from a target time to an initial time is caused to reverse-generate the contingency tables in an order from the initial time to the target time. Reverse-generation is caused by recursively: (i) subdividing a sequence of time steps by a factor of at least two into successively smaller sub-sequences, (ii) iterating in a computational iteration order over each recursively subdivided sub-sequence, and (iii) generating a contingency table closest in time to the initial time for the recursive iteration over each recursively subdivided sub-sequence.

Abstract: Example methods and systems for determining when to launch vehicles into a fleet of autonomous vehicles are described. A method comprises receiving a sequence of coverage requirements for a region over a period of time. The region may be characterized by landmarks and the period of time can be divided into time intervals. The method also includes defining a landmark as a launch site representative of a landmark at which a given vehicle can be added to a plurality of operating vehicles, and determining for a respective landmark, estimated landmarks that can be reached by a vehicle starting from the respective landmark by an end of a time interval. The method also includes based on the sequence of coverage requirements and the estimated landmarks, determining a given launch site and corresponding time interval at which to add the given vehicle to the plurality of operating vehicles.

Abstract: This disclosure relates to the use of a method for determining communication timing of an aerial vehicle, such as a balloon. The method includes determining a trajectory of an aerial vehicle. Additionally, the method includes, based on the trajectory, determining a transmission trigger for a location-report message such that a location-report message transmission that is responsive to the transmission trigger has at least a predefined probability of occurring before the aerial vehicle contacts the ground. Further, the method also includes, responsive to the transmission trigger, transmitting the location-report message, where the location-report message comprises location data from the aerial vehicle.

Abstract: Methods and systems for determining trajectories for vehicles of a fleet of vehicles are provided. In one example, a method comprises receiving an initial location of one or more vehicles, and receiving a sequence of coverage requirements for a region and an associated period of time. The region may be divided into a plurality of landmarks and the period of time may be divided into a plurality of phases. The method also comprises determining for each of one or more phases and at least one respective landmark, a set of starting landmarks from which a vehicle could reach the respective landmark during the phase. The method further comprises determining which respective landmark that the vehicle should travel to during the one or more phases based on the sequence of coverage requirements and the set of starting landmarks for the one or more phases and the at least one respective landmark.

Abstract: Methods and systems for determining trajectories for vehicles of a fleet of vehicles are provided. In one example, a method comprises receiving an initial location of one or more vehicles, and receiving a sequence of coverage requirements for a region and an associated period of time. The region may be divided into a plurality of landmarks and the period of time may be divided into a plurality of phases. The method also comprises determining for each of one or more phases and at least one respective landmark, a set of starting landmarks from which a vehicle could reach the respective landmark during the phase. The method further comprises determining which respective landmark that the vehicle should travel to during the one or more phases based on the sequence of coverage requirements and the set of starting landmarks for the one or more phases and the at least one respective landmark.

Abstract: Methods and systems for determining a cyclical pattern of trajectories for a fleet of vehicles are provided. In one example, a method comprises receiving a sequence of coverage requirements for a region and an associated period of time. For each of one or more phases of the period of time, possible routes that a vehicle located at one or more respective landmarks at a beginning of the phase could follow to reach one or more additional landmarks by an end of the phase are determined. Further, a cyclical pattern of trajectories for vehicles of a fleet of vehicles that minimizes a difference between a distribution of the fleet at a beginning of the period of time and a distribution of the fleet at an end of the period of time is determined.

Abstract: Example methods and systems for decomposing fleet planning optimizations via spatial partitions are described. An example method includes receiving information indicating a sequence of coverage requirements for a region over a period of time. The region is characterized by a plurality of landmarks and the period of time is divided into a plurality of phases. An individual coverage requirement indicates a desired number of vehicles of a plurality of vehicles for respective landmarks at a given phase. The method also includes dividing the region into a plurality of sub-regions, and determining sub-region fleet plans for the plurality of sub-regions based on estimates of one or more vehicles entering respective sub-regions and estimates of one or more vehicles leaving respective sub-regions. The method also includes combining the sub-region fleet plans to produce a fleet plan responsive to the sequence of coverage requirements for the region.

Abstract: Methods and systems for determining trajectories for a fleet of vehicles are provided. In one example, a method comprises receiving an initial location of one or more vehicles, and receiving a sequence of coverage requirements for a region and an associated period of time. The method also comprises determining, for each of one or more phases, single-phase landmarks that a vehicle could travel to over the duration of the phase, and determining for at least one of the one or more phases, phase-skipping landmarks that a vehicle could travel to over the duration of multiple phases. The method further comprises determining which landmarks of the single-phase landmarks and phase-skipping landmarks that a vehicle should travel to based on the initial locations of the one or more vehicles and the sequence of coverage requirements.