Collision prevention flight control mode
Systems and methods for controlling an aerial vehicle to avoid obstacles are disclosed. A system can detect, based on a world model generated from sensor data captured by one or more sensors positioned on the aerial vehicle during flight, an obstacle for the aerial vehicle, and trigger an augmented manual control mode responsive to a speed of the aerial vehicle being less than a predetermined threshold and detecting the obstacle. The system can set, responsive to triggering the augmented manual control mode, a speed constraint for the aerial vehicle in a direction of the obstacle based on a distance between the aerial vehicle and the obstacle. The system can receive an instruction to navigate the aerial vehicle in the direction at a second speed, and adjust the instruction to replace the second speed with the speed constraint, causing the aerial vehicle to navigate at the speed constraint.
1. A method for controlling an aerial vehicle to avoid obstacles, comprising:
generating, by one or more processors coupled to memory of the aerial vehicle, using sensor data captured by one or more sensors of the aerial vehicle, a multi-dimensional distance field comprising a plurality of coordinates, each coordinate of the plurality of coordinates having a distance value indicating a distance between the aerial vehicle and an obstacle;
detecting, by the one or more processors, based on the multi-dimensional distance field, the obstacle for the aerial vehicle;
triggering, by the one or more processors, an augmented manual control mode responsive to a speed of the aerial vehicle being less than a predetermined threshold and detecting the obstacle;
determining, by the one or more processors responsive to triggering the augmented manual control mode, a speed constraint for the aerial vehicle in a direction of the obstacle derived from at least one gradient of the multi-dimensional distance field, the speed constraint determined based on a turn coordination speed limit of the aerial vehicle and a distance between the aerial vehicle and the obstacle;
receiving, by the one or more processors via an inceptor of the aerial vehicle, an instruction to navigate the aerial vehicle in the direction at a second speed greater than the speed constraint; and
adjusting, by the one or more processors, the instruction to replace the second speed with the speed constraint, to cause the aerial vehicle to navigate in the direction at the speed constraint instead of the second speed.
2. The method of claim 1 , wherein the one or more sensors comprise one or more of a light detection and ranging (LiDAR) sensor, a radar sensor, or a camera.
3. The method of claim 1 , wherein the obstacle is a first obstacle, and further comprising:
detecting, by the one or more processors, a second obstacle for the aerial vehicle in a second direction that is at least partially opposite the direction; and
adjusting, by the one or more processors, a second instruction received via the inceptor of the aerial vehicle to limit a third speed for the aerial vehicle in the second direction, to guide the aerial vehicle between the first obstacle and the second obstacle.
4. The method of claim 1 , further comprising:
determining, by the one or more processors, that the distance is less than a predetermined distance threshold; and
setting, by the one or more processors, the speed constraint to prevent movement in the direction responsive to determining that the distance is less than the predetermined distance threshold.
5. The method of claim 1 , further comprising providing, by the one or more processors, an alert to a pilot of the aerial vehicle responsive to setting the speed constraint, wherein the alert is at least one of haptic feedback, an audio alert, or a visual alert presented on a display of the aerial vehicle.
6. The method of claim 1 , further comprising adjusting, by the one or more processors, an inceptor constraint to limit physical movement of the inceptor based on the speed constraint.
7. The method of claim 1 , further comprising:
setting, by the one or more processors responsive to triggering the augmented manual control mode, an attitude constraint for the aerial vehicle based on the direction to the obstacle and the distance; and
adjusting, by the one or more processors responsive to receiving a second instruction to change an attitude of the aerial vehicle, the second instruction to replace the change of the attitude with the attitude constraint.
8. The method of claim 1 , further comprising:
setting, by the one or more processors responsive to triggering the augmented manual control mode, a vertical acceleration constraint for the aerial vehicle based on the direction to the obstacle and the distance; and
adjusting, by the one or more processors responsive to receiving a second instruction to change a vertical acceleration of the aerial vehicle, the second instruction to replace the change of the vertical acceleration with the vertical acceleration constraint.
9. The method of claim 1 , wherein determining the speed constraint for the aerial vehicle further comprises determining, by the one or more processors, a respective speed constraint for each of an x-axis direction, a y-axis direction, and a z-axis direction.
10. A system for controlling an aerial vehicle to avoid obstacles, comprising:
one or more processors coupled to memory of the aerial vehicle, the one or more processors configured to:
generate, using sensor data captured by one or more sensors of the aerial vehicle, a multi-dimensional distance field comprising a plurality of coordinates, each coordinate of the plurality of coordinates having a distance value indicating a distance between the aerial vehicle and an obstacle;
detect, based on the multi-dimensional distance field, the obstacle for the aerial vehicle;
trigger an augmented manual control mode responsive to a speed of the aerial vehicle being less than a predetermined threshold and detecting the obstacle;
determine, responsive to triggering the augmented manual control mode, a speed constraint for the aerial vehicle in a direction of the obstacle derived from at least one gradient of the multi-dimensional distance field, the speed constraint determined based on a turn coordination speed limit of the aerial vehicle and a distance between the aerial vehicle and the obstacle;
receive, via an inceptor of the aerial vehicle, an instruction to navigate the aerial vehicle in the direction at a second speed greater than the speed constraint; and
adjust the instruction to replace the second speed with the speed constraint, to cause the aerial vehicle to navigate in the direction at the speed constraint instead of the second speed.
11. The system of claim 10 , wherein the one or more sensors comprise one or more of a light detection and ranging (LiDAR) sensor, a radar sensor, or a camera.
12. The system of claim 10 , wherein the obstacle is an first obstacle, and the one or more processors are further configured to:
detect a second obstacle for the aerial vehicle in a second direction that is at least partially opposite the direction; and
adjust a second instruction received via the inceptor of the aerial vehicle to limit a third speed for the aerial vehicle in the second direction, to guide the aerial vehicle between the first obstacle and the second obstacle.
13. The system of claim 10 , wherein the one or more processors are further configured to:
determine that the distance is less than a predetermined distance threshold; and
set the speed constraint to prevent movement in the direction responsive to determining that the distance is less than the predetermined distance threshold.
14. The system of claim 10 , wherein the one or more processors are further configured to provide an alert to a pilot of the aerial vehicle responsive to setting the speed constraint, wherein the alert is at least one of haptic feedback, an audio alert, or a visual alert presented on a display of the aerial vehicle.
15. The system of claim 10 , wherein the one or more processors are further configured to adjust an inceptor constraint to limit physical movement of the inceptor based on the speed constraint.
16. The system of claim 10 , wherein the one or more processors are further configured to:
set, responsive to triggering the augmented manual control mode, an attitude constraint for the aerial vehicle based on the direction to the obstacle and the distance; and
adjust, responsive to receiving a second instruction to change an attitude of the aerial vehicle, the second instruction to replace the change of the attitude with the attitude constraint.
17. The system of claim 10 , wherein the one or more processors are further configured to:
set, responsive to triggering the augmented manual control mode, a vertical acceleration constraint for the aerial vehicle based on the direction to the obstacle and the distance; and
adjust, responsive to receiving a second instruction to change a vertical acceleration of the aerial vehicle, the second instruction to replace the change of the vertical acceleration with the vertical acceleration constraint.
18. The system of claim 10 , wherein the one or more processors are further configured to determine the speed constraint for the aerial vehicle by determining a respective speed constraint for each of an x-axis direction, a y-axis direction, and a z-axis direction.