Granted Patent B1

US 12,315,233 · App. 18/079,869 · Granted May 27, 2025

Inventor: Robi Sen (Richland, WA)

G06V10/776G05D1/042G06V10/141G06V10/82G06V10/70

Abstract

Claims (23)

1. A method to manipulate a vehicle that employs one or more optical sensors for autonomous navigation, the method comprising:

receiving measurements from at least one sensor that is responsive to the vehicle's movement;

employing an artificial neural network (ANN) to adapt a modulation pattern used to modulate an array of light emitters;

transmitting the modulation pattern from the array of light emitters to the one or more optical sensors; and

determining, from the measurements, if the modulation pattern affects the vehicle's movement and configuring the ANN to adapt the modulation pattern to cause a predetermined type of movement.

2. The method of claim 1 , wherein the at least sensor comprises at least one of a camera, an optical sensor, a LIDAR, a RADAR, or an acoustic sensor.

3. The method of claim 1 , wherein receiving measurements comprises measuring the vehicle's movement.

4. The method of claim 3 , wherein measuring the vehicle's movement comprises measuring at least one of yaw, pitch, roll, heading, speed, velocity, altitude, acceleration, deceleration, vibration, ascent, descent, or derivatives thereof with respect to time.

5. The method of claim 1 , wherein the vehicle is an unmanned aerial vehicle, a ground vehicle, a boat, a submarine, or a missile.

6. The method of claim 1 , wherein the light emitters comprise at least one of light-emitting diodes and lasers.

7. The method of claim 1 , wherein the array is a linear array, a planar array, or a volumetric array.

8. The method of claim 1 , wherein the modulation pattern comprises at least one of amplitude modulation, on-off keying, frequency modulation, phase modulation, index modulation, or spatial modulation.

9. The method of claim 8 , wherein the spatial modulation comprises at least one of linear modulation, planar modulation, or volumetric modulation.

10. The method of claim 1 , wherein determining, from the measurements, if the modulation pattern affects the vehicle's movement comprises producing labeled data sets comprising modulation patterns as input data and measurements of the vehicle's movement as associated ground truths.

11. The method of claim 1 , wherein the ANN is a deep-learning neural network.

12. The method of claim 1 , further comprising configuring the array of light emitters to affect only a portion of the one or more optical sensors' field of view.

13. A method of disrupting a navigation system that employs a camera, the method comprising:

receiving output signals from the navigation system comprising at least one of image-processing outputs and navigation signals;

configuring an array of light emitters to occupy a portion of a field of view of the camera;

employing an artificial neural network (ANN) to adapt a modulation pattern of light emitted by the array; and

determining, from the output signals, if the modulation pattern affects at least one of image processing or navigation control performed in the navigation system and configuring the ANN to adapt the modulation pattern to cause a predetermined type of movement.

14. The apparatus of claim 13 , wherein the image-processing outputs comprise outputs of a camera neural network that is responsive to an image captured by the camera; wherein the ANN denotes a target image-processing output as a ground truth; and wherein the ANN computes an error function as a difference between the image-processing outputs and the ground truth.

15. The apparatus of claim 14 , wherein the ANN performs gradient descent to update the modulation pattern, the gradient descent comprising a function of the error function.

Assignments (3)

Continuity (1)

References Cited (49)