Controlling unmanned aerial vehicles to avoid obstacle collision
First Claim
1. A method for controlling an unmanned aerial vehicle (UAV) to avoid obstacle collision, comprising:
- (a) acquiring range data of a real-world scene using one or more range sensors, wherein the range data comprises depth data to one or more visible objects;
(b) combining the range data into an egospace representation comprising a first set of one or more pixels in egospace, wherein;
(1) each pixel in the first set of one or more pixels corresponds to a specific direction;
(2) each pixel in the first set of one or more pixels stores a depth;
(3) the depth comprises a distance, to one of the one or more visible objects encountered in the specific direction; and
(4) the egospace comprises a coordinate system given by a second set of all possible pixel and depth combinations;
(c) expanding an apparent size of each of the one or more visible objects based on a dimension of the UAV, wherein the UAV comprises a configuration flat vehicle (CFV), wherein a UAV with state variables x, control inputs u, and state equations {dot over (x)}=f (x,u) comprises a CFV if there exists a set of flat outputs
z=α
(x,u,{dot over (u)}, . . . ,u(k)),that are a smooth function α
of the state variables and control inputs, smooth functions β and
γ
such that
x=β
(z,ż
, . . . ,z(j)),
u=γ
(z,ż
, . . . ,z(j)),and obstacle and configuration spaces O, C⊂
{z} such that C={z}\O;
(d) receiving an assigned destination in the real world scene based on world space;
(e) transforming the assigned destination into egospace coordinates in egospace;
(f) generating a trackable path from the UAV to the assigned destination through egospace that avoids collision with the one or more visible objects based on the expanded apparent sizes of each of the one or more visible objects; and
(g) identifying and providing one or more inputs to control the UAV to follow the trackable path, and wherein the UAV follows the trackable path based on the one or more inputs.
2 Assignments
0 Petitions
Accused Products
Abstract
A method, device, framework, and system provide the ability to control an unmanned aerial vehicle (UAV) to avoid obstacle collision. Range data of a real-world scene is acquired using range sensors (that provide depth data to visible objects). The range data is combined into an egospace representation (consisting of pixels in egospace). An apparent size of each of the visible objects is expanded based on a dimension of the UAV. An assigned destination in the real world scene based on world space is received and transformed into egospace coordinates in egospace. A trackable path from the UAV to the assigned destination through egospace that avoids collision with the visible objects (based on the expanded apparent sizes of each of the visible objects) is generated. Inputs that control the UAV to follow the trackable path are identified.
-
Citations
12 Claims
-
1. A method for controlling an unmanned aerial vehicle (UAV) to avoid obstacle collision, comprising:
-
(a) acquiring range data of a real-world scene using one or more range sensors, wherein the range data comprises depth data to one or more visible objects; (b) combining the range data into an egospace representation comprising a first set of one or more pixels in egospace, wherein; (1) each pixel in the first set of one or more pixels corresponds to a specific direction; (2) each pixel in the first set of one or more pixels stores a depth; (3) the depth comprises a distance, to one of the one or more visible objects encountered in the specific direction; and (4) the egospace comprises a coordinate system given by a second set of all possible pixel and depth combinations; (c) expanding an apparent size of each of the one or more visible objects based on a dimension of the UAV, wherein the UAV comprises a configuration flat vehicle (CFV), wherein a UAV with state variables x, control inputs u, and state equations {dot over (x)}=f (x,u) comprises a CFV if there exists a set of flat outputs
z=α
(x,u,{dot over (u)}, . . . ,u(k)),that are a smooth function α
of the state variables and control inputs, smooth functions β and
γ
such that
x=β
(z,ż
, . . . ,z(j)),
u=γ
(z,ż
, . . . ,z(j)),and obstacle and configuration spaces O, C⊂
{z} such that C={z}\O;(d) receiving an assigned destination in the real world scene based on world space; (e) transforming the assigned destination into egospace coordinates in egospace; (f) generating a trackable path from the UAV to the assigned destination through egospace that avoids collision with the one or more visible objects based on the expanded apparent sizes of each of the one or more visible objects; and (g) identifying and providing one or more inputs to control the UAV to follow the trackable path, and wherein the UAV follows the trackable path based on the one or more inputs. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A navigation framework in an unmanned aerial vehicle that avoids obstacle collision:
-
(a) an embedded flight computer integrated into the UAV that enables the UAV to maneuver, wherein the UAV; (1) acquires range data of a real-world scene using one or more range sensors mounted on the UAV, wherein the range data comprises depth data to one or more visible objects; (2) combines the range data into an egospace representation comprising a first set of one or more pixels in egospace, wherein; (A) each pixel in the first set of one or more pixels corresponds to a specific direction; (B) each pixel in the first set of one or more pixels stores a depth; (C) the depth comprises a distance, to one of the one or more visible objects encountered in the specific direction; and (D) the egospace comprises a coordinate system given by a second set of all possible pixel and depth combinations; (3) expands an apparent size of each of the one or more visible objects based on a dimension of the UAV, wherein the UAV comprises a configuration flat vehicle (CFV), wherein a UAV with state variables x, control inputs u, and state equations {dot over (x)}=f (x,u) comprises a CFV if there exists a set of flat outputs
z=α
(x,u,{dot over (u)}, . . . ,u(k)),that are a smooth function α
of the state variables and control inputs, smooth functions β and
γ
such that
x=β
(z,ż
, . . . ,z(j)),
u=γ
(z,ż
, . . . ,z(j)),and obstacle and configuration spaces O, C⊂
{z} such that C={z}\O;(4) receives an assigned destination in the real world scene based on world space; (5) transforms the assigned destination into egospace coordinates in egospace; (6) generates a trackable path from the UAV to the assigned destination through egospace that avoids collision with the one or more visible objects based on the expanded apparent sizes of each of the one or more visible objects; and (7) identifies and provides one or more inputs to control the UAV to follow the trackable path, and wherein the UAV follows the trackable path based on the one or more inputs. - View Dependent Claims (8, 9, 10, 11, 12)
-
Specification