Method and apparatus for object detection with integrated environmental information

Patent metadata

Field	Value
Publication number	US-11050162-B2
Application number	US-201816208496-A
Country	US
Kind code	B2
Filing date	Dec 3, 2018
Priority date	Dec 2, 2017
Publication date	Jun 29, 2021
Grant date	Jun 29, 2021

Abstract

Examples disclosed herein relate to a sensor fusion system for use in an autonomous vehicle. The sensor fusion system has a radar detection unit with a metastructure antenna to direct a beamform in a field-of-view (“FoV”) of the vehicle, an analysis module to receive information about a detected object and determine control actions for the radar detection unit and the metastructure antenna based on the received information and on environmental information, and an autonomous control unit to control actions of the vehicle based on the received information and the environmental information.

First claim

What is claimed is:

1. A sensor fusion system for use in an autonomous vehicle, comprising:
a radar detection unit comprising a metastructure antenna configured to direct a beamform in a field-of-view (“FoV”) of the vehicle;
an analysis module configured to receive information about a detected object and determine a plurality of control actions based on the received information and environmental information for the radar detection unit and the metastructure antenna, wherein the analysis module is a neural network that predicts a condition using the received information and environmental information; and
an autonomous control unit configured to control one or more actions of the vehicle based on the received information and the environmental information and at a direction of the analysis module.

2. The sensor fusion system of claim 1 , further comprising a camera detection unit and a lidar detection unit.

3. The sensor fusion system of claim 1 , wherein one of the plurality of control actions includes directing the radar detection unit to change a width of the beamform and direct it toward the detected object and the one or more actions of the vehicle controlled by the autonomous control unit at the direction of the analysis module includes changing lanes.

4. The sensor fusion system of claim 1 , further comprising a library that stores the environmental information, object detection information and object detection rules.

5. The sensor fusion system of claim 1 , wherein the metastructure antenna comprises a plurality of subarrays of metastructure cells configured to radiate the beamform.

6. The sensor fusion system of claim 5 , wherein at least one of the metastructure cells comprises a reactance control mechanism.

7. The sensor fusion system of claim 6 , wherein the reactance control mechanism is a varactor coupled between a conductive area and a conductive loop in the at least one metastructure cell.

8. The sensor fusion system of claim 7 , wherein the radar detection unit comprises a subarray controller configured to control a voltage applied to the varactor to change the beamform.

9. The sensor fusion system of claim 1 , wherein the environmental information comprises topographical information and the analysis module is configured to direct the metastructure antenna to change a vertical range in response to a change in elevation in the topographical information.

10. The sensor fusion system of claim 1 , further comprising a learning module configured to train the neural network.

11. A metastructure antenna system for use in a radar detection unit in an autonomous vehicle, comprising:
an antenna feed configured to receive a transmission signal and distribute the transmission signal to a plurality of transmission lines in a transmission array;
a metastructure antenna comprising a plurality of subarrays of metastructure cells configured to radiate the transmission signal into a beamform that enables a detection of an object in a field-of-view of the autonomous vehicle;
a subarray controller configured to control a plurality of subarrays of the metastructure antenna to radiate the transmission signal based on the detected object and environmental information surrounding the detected object; and
an analysis module comprising a neural network that receives information of the detected object and the environmental information and predicts a condition based on the information of the detected object and the environmental information, wherein the analysis module applies rules for controlling the plurality of subarrays of the metastructure antenna via the subarray controller based on the information of the detected object.

12. The metastructure antenna system of claim 11 , wherein at least one of the metastructure cells comprises a varactor coupled between a conductive area and a conductive loop in the at least one metastructure cell.

13. The metastructure antenna system of claim 11 , wherein the subarray controller is configured to apply a voltage to at least one metastructure cell in a subarray to change a direction of the beamform.

14. The metastructure antenna system of claim 11 , wherein the plurality of subarrays are arranged in layers.

15. The metastructure antenna system of claim 11 , wherein the metastructure cells are metamaterial cells organized in a lattice.

16. The metastructure antenna system of claim 11 , wherein the environmental information comprises topographical information and the subarray controller is configured to direct the metastructure antenna to change a vertical range in response to a change in elevation in the topographical information.

17. A method to detect an object in a field-of-view of an autonomous vehicle, comprising:
determining a location of the vehicle;
gathering environmental information in a path and surrounding environment of the vehicle;
comparing the environmental information to previous environmental data;
detecting an elevation change;
directing, via an analysis module, a metastructure antenna based on detected elevation change, wherein the analysis module comprises a neural network; and
changing a vertical scan of the metastructure antenna in the vehicle.

18. The method of claim 17 , wherein the environmental information comprises topographical information.

19. The method of claim 17 , wherein changing the vertical scan of the metastructure antenna comprises changing a voltage applied to at least one cell of the metastructure antenna to change a reactance of the at least one cell.

20. The method of claim 17 , wherein changing the vertical scan of the metastructure antenna comprises changing a voltage applied to a plurality of metastructure cells in at least one subarray of the metastructure antenna.

Assignees

• Metawave Corp

Inventors

• Achour Maha
• Daniel George

Classifications

• G01S13/867 Primary

  Combination of radar systems with cameras · CPC title

• G01S13/02

  Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems · CPC title

• G01S13/931

  of land vehicles · CPC title

• G01S2013/0263

  Passive array antenna · CPC title

• G01S7/417

  involving the use of neural networks · CPC title