Systems and methods to determine flight paths for aerial vehicles based on risk
Described are example systems and methods generally directed to systems and methods for determining and managing flight planning and operations for unmanned vehicles, such as unmanned aerial vehicles (UAVs). The described systems and methods can facilitate generation of a risk-weighted model of an environment in which vehicles may operate to facilitate determination of a total cumulative risk associated with certain flight paths between an origin and a destination in the environment. The total cumulative risk associated with a flight path can include a risk associated risks present on the ground along the flight path, as well as risks associated with the vehicle performing the flight. The total cumulative risk for a given flight path can be used to identify flight paths presenting the lowest relative risk and can also be compared against a risk threshold to determine whether the total cumulative risk associated with the flight path is within an acceptable range.
1 . A computer-implemented method, comprising:
obtaining, from a computing device, a source location;
obtaining, from the computing device, a delivery destination;
determining a threshold risk;
determining a flight path forming at least a portion of a flight between the source location and the delivery destination;
obtaining ground information associated with the flight path;
determining a ground risk associated with the flight path based at least in part on the ground information;
obtaining vehicle information associated with the flight path;
determining a vehicle risk associated with the flight path based at least in part on the vehicle information;
determining a cumulative risk associated with the flight path based at least in part on the ground risk and the vehicle risk;
comparing the cumulative risk associated with the flight path against the threshold risk;
in response to determining that the cumulative risk associated with the flight path is below the threshold risk, causing an aerial vehicle to operate a flight via the determined flight path; and
in response to determining that the cumulative risk associated with the flight path is above the threshold risk, determining that the aerial vehicle is not to operate the flight via the determined flight path and returning, to the computing device, an indication that aerial delivery is unavailable for the source location and the ground location.
2 . The computer-implemented method of claim 1 , further comprising:
determining a second flight path forming at least a second portion of the flight between the source location and the delivery destination;
determining a second cumulative risk associated with the second flight path;
comparing the cumulative risk associated with the flight path against the second cumulative risk associated with the second flight path; and
selecting one of the flight path or the second flight path as a preferred flight path based at least in part on the cumulative risk associated with the flight path and the second cumulative risk associated with the second flight path.
3 . The computer-implemented method of claim 2 , further comprising:
determining a third flight path forming at least a third portion of the flight between the source location and the delivery destination;
determining a third cumulative risk associated with the third flight path;
determining a fourth flight path forming at least a fourth portion of the flight between the source location and the delivery destination;
determining a fourth cumulative risk associated with the fourth flight path;
comparing the third cumulative risk associated with the third flight path against the fourth cumulative risk associated with the fourth flight path; and
selecting one of the third flight path or the fourth flight path as a next path of the preferred flight path based at least in part on the third cumulative risk associated with the third flight path and the fourth cumulative risk associated with the fourth flight path.
4 . The computer-implemented method of claim 1 , wherein:
the ground risk represents a probability of causing harm to a person; and
the vehicle risk represents a probability of experiencing a vehicle failure.
5 . The computer-implemented method of claim 1 , wherein:
ground information includes at least one of:
a population density;
a presence of a sensitive structure; or
an indication of an event that temporarily increases population density; and
vehicle information includes at least one of:
a flight duration;
at least one vehicle parameter; or
at least one flight path parameter.
6 . A computing system, comprising:
one or more processors;
a memory coupled to the one or more processors and storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least:
determine a source location and a delivery location;
generate a risk-weighted model representing a cumulative flight risk associated with an environment associated with the source location and the delivery location, the cumulative flight risk based at least in part on a ground risk and a vehicle risk;
determine a preferred flight path within the environment based at least in part on the cumulative flight risk associated with environment;
obtain a threshold flight risk;
compare the cumulative flight risk with the threshold flight risk;
in response to a first determination that the cumulative flight risk is below the threshold flight risk, cause an aerial vehicle to operate a flight via the preferred flight path; and
in response to a second determination that the cumulative flight risk is above the threshold flight risk, determine that the aerial vehicle is not to operate the flight via the preferred flight path and return, to a computing device, an indication that aerial delivery is unavailable for the source location and the delivery ground location.
7 . The computing system of claim 6 , wherein determination that the cumulative flight risk is below the threshold flight risk is performed incrementally.
8 . The computing system of claim 6 , wherein determination of the preferred flight path is further based at least in part on at least one of an economic cost or a time duration.
9 . The computing system of claim 6 , wherein the preferred flight path is incrementally determined based at least in part on the risk-weighted model using at least one of an A* algorithm or a gradient descent algorithm.
10 . The computing system of claim 6 , wherein the risk-weighted model includes a risk-weighted four-dimensional graph representing an incremental cumulative flight risk within the environment and the four dimensions include a position and a time.
11 . The computing system of claim 6 , wherein:
the ground risk is based at least in part on at least one of:
a population density;
a presence of a sensitive structure; or
an indication of an event that temporarily increases population density; and
the vehicle risk is based at least in part on at least one of:
a flight duration;
at least one vehicle parameter; or
at least one flight path parameter.
12 . The computing system of claim 6 , wherein the risk-weighted model includes a plurality of cumulative flight risks associated with a plurality of flight paths within the environment.
13 . The computing system of claim 12 , wherein the plurality of cumulative flight risks includes a first cumulative flight risk associated with a first flight path from the plurality of flight paths and a second cumulative flight risk associated with a second flight path from the plurality of flight paths, and determination of the preferred flight path includes a comparison of the first cumulative flight risk and the second cumulative flight risk.
14 . The computing system of claim 13 , wherein comparison of the first cumulative flight risk and the second cumulative flight risk is performed incrementally.
15 . A computer-implemented method, comprising:
receiving a request from a client device in connection with an item offered on an electronic commerce platform;
obtaining a delivery destination corresponding to a user associated with the client device;
determining a source location associated with the item;
determining a flight path between the source location and the delivery destination;
obtaining ground information associated with the flight path;
determining a ground risk associated with the flight path based at least in part on the ground information;
obtaining vehicle information associated with the flight path;
determining a vehicle risk associated with the flight path based at least in part on the vehicle information;
determining a cumulative risk associated with the flight path based at least in part on the ground risk and the vehicle risk;
comparing the cumulative risk against a threshold risk;
in response to determining that the cumulative risk associated with the flight path is below the threshold risk:
sending for presentation on the client device an aerial delivery option in connection with the item; and
initiating an aerial delivery of the item from the source location to the delivery destination via the flight path; and
in response to determining that the cumulative risk associated with the flight path is above the threshold risk, sending for presentation on the client device an indication that aerial delivery is unavailable in connection with the item.
16 . The computer-implemented method of claim 15 , wherein the cumulative risk associated with the flight path is determined incrementally to include a lowest relative cumulative risk.
17 . The computer-implemented method of claim 15 , further comprising:
determining that the cumulative risk includes a time-dependent factor;
determining a time at which the cumulative risk no longer includes the time-dependent factor; and
sending for presentation on the client device an indication that aerial delivery is available at the time.
18 . The computing system of claim 6 , wherein the vehicle risk represents a probability of vehicle failure based at least in part on vehicle information.