Drone path planning
Various systems and methods for drone path planning are described herein. A system for drone path planning for a drone, the system to perform the operations: storing a current location of the drone as a current waypoint in a set of waypoints, the set of waypoints to include the current waypoint and a previous waypoint; detecting a current set of frontiers from the current location; storing the current set of frontiers in a list of active goals, the current set of frontiers associated with the current location; determining whether a target is discovered in the current set of frontiers; exploring the current set of frontiers to attempt to find the target; and exploring a previous set of frontiers from the list of active goals, when exploring the current set of frontiers does not, discover the target, the previous set of frontiers associated with the previous waypoint.
1. A system for drone path planning for a drone, the system comprising:
a processor subsystem; and
memory comprising instructions, which when executed by the processor subsystem, cause the processor subsystem to perform the operations comprising:
storing a current location of the drone as a current waypoint in a set of waypoints, the set of waypoints to include the current waypoint and a previous waypoint;
detecting a current set of frontiers from the current location;
storing the current set of frontiers in a list of active goals, the current set of frontiers associated with the current location;
determining whether a target is discovered in the current set of frontiers;
exploring the current set of frontiers to attempt to find the target; and
exploring a previous set of frontiers from the list of active goals, when exploring the current set of frontiers does not discover the target, the previous set of frontiers associated with the previous waypoint.
2. The system of claim 1 , wherein the current set of frontiers are regions that spatially extend an environmental model.
3. The system of claim 1 , wherein detecting the current set of frontiers comprises:
using a sensor to detect the current set of frontiers.
4. The system of claim 3 , wherein the sensor comprises a light detecting and ranging sensor.
5. The system of claim 3 , wherein the sensor comprises a depth camera.
6. The system of claim 1 , wherein determining whether the target is discovered comprises:
using image analysis to determine whether the target is in a field-of-view of the drone.
7. The system of claim 1 , wherein exploring the current set of frontiers comprises:
exploring each frontier in the current set of frontiers.
8. The system of claim 1 , wherein exploring the current set of frontiers comprises:
from a given frontier in the current set of frontiers, storing the given frontier as a new waypoint in the set of waypoints and detecting additional frontiers from the given frontier, and processing the additional frontiers.
9. The system of claim 1 , wherein exploring the current set of frontiers comprises:
maintaining the list of active goals as the frontiers in the current set of frontiers are explored.
10. The system of claim 1 , wherein exploring the previous set of frontiers comprises:
navigating the drone to the previous waypoint; and
exploring the previous set of frontiers from the previous waypoint.
11. The system of claim 1 , further comprising:
rotating the drone to capture additional frontiers from a particular waypoint; and
exploring the additional frontiers.
12. The system of claim 1 , wherein the target is a human user.
13. The system of claim 1 , wherein the target is a geographic location.
14. At least one non-transitory machine-readable medium including instructions for drone path planning for a drone, which when executed by a machine, cause the machine to perform the operations comprising:
storing a current location of the drone as a current waypoint in a set of waypoints, the set of waypoints to include the current waypoint and a previous waypoint;
detecting a current set of frontiers from the current location;
storing the current set of frontiers in a list of active goals, the current set of frontiers associated with the current location;
determining whether a target is discovered in the current set of frontiers;
exploring the current set of frontiers to attempt to find the target; and
exploring a previous set of frontiers from the list of active goals, when exploring the current set of frontiers does not discover the target, the previous set of frontiers associated with the previous waypoint.
15. The machine-readable medium of claim 14 , wherein the current set of frontiers are regions that spatially extend an environmental model.
16. The machine-readable medium of claim 14 , wherein detecting the current set of frontiers comprises:
using a sensor to detect the current set of frontiers.
17. The machine-readable medium of claim 16 , wherein the sensor comprises a light detecting and ranging sensor.
18. The machine-readable medium of claim 16 , wherein the sensor comprises a depth camera.
19. The machine-readable medium of claim 14 , wherein determining whether the target is discovered comprises:
using image analysis to determine whether the target is in a field-of-view of the drone.
20. The machine-readable medium of claim 14 , wherein exploring the current set of frontiers comprises:
exploring each frontier in the current set of frontiers.
21. The machine-readable medium of claim 14 , wherein exploring the current set of frontiers comprises:
from a given frontier in the current set of frontiers, storing the given frontier as a new waypoint in the set of waypoints and detecting additional frontiers from the given frontier, and processing the additional frontiers.
22. The machine-readable medium of claim 14 , wherein exploring the current set of frontiers comprises:
maintaining the list of active goals as the frontiers in the current set of frontiers are explored.
23. The machine-readable medium of claim 14 , wherein exploring the previous set of frontiers comprises:
navigating the drone to the previous waypoint; and
exploring the previous set of frontiers from the previous waypoint.
24. A method of drone path planning for a drone, the method comprising:
storing a current location of the drone as a current waypoint in a set of waypoints, the set of waypoints to include the current waypoint and a previous waypoint;
detecting a current set of frontiers from the current location;
storing the current set of frontiers in a list of active goals, the current set of frontiers associated with the current location;
determining whether a target is discovered in the current set of frontiers;
exploring the current set of frontiers to attempt to find the target; and
exploring a previous set of frontiers from the list of active goals, when exploring the current set of frontiers does not discover the target, the previous set of frontiers associated with the previous waypoint.
25. The method of claim 24 , wherein exploring the current set of frontiers comprises:
from a given frontier in the current set of frontiers, storing the given frontier as a new waypoint in the set of waypoints and detecting additional frontiers from the given frontier, and processing the additional frontiers.