Semantic information sharing in autonomous vehicles

Patent metadata

Field	Value
Publication number	US-11475763-B2
Application number	US-202016791748-A
Country	US
Kind code	B2
Filing date	Feb 14, 2020
Priority date	Feb 15, 2019
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

Systems and methods are disclosed for a semantic information sharing within a group of autonomous ground vehicles. In some embodiments, a method may include sensing an environment near a first autonomous vehicle to produce first environmental data; creating a first mathematical model representing the environment near the first autonomous vehicle based on the first environmental data; sending a request for additional environmental data to a second autonomous vehicle; receiving a second mathematical model from the second autonomous vehicle; and merging the second mathematical model with the first mathematical model.

First claim

That which is claimed:

1. A method comprising:
sensing an environment near a first autonomous vehicle to produce first environmental data;
creating a first mathematical model representing the environment near the first autonomous vehicle based on the first environmental data;
sending a request for additional environmental data to a second autonomous vehicle;
receiving a second mathematical model from the second autonomous vehicle;
merging the second mathematical model with the first mathematical model;
sharing the merged mathematical model with a group of autonomous vehicles, wherein the group of autonomous vehicles comprises at least the first autonomous vehicle and the second autonomous vehicle; and
controlling, via a control system, the group of autonomous vehicles based on the merged mathematical model, by increasing control horizon of the group of autonomous vehicles, wherein the control system comprises a controller and a plurality of distinct control systems.

2. The method according to claim 1 , wherein the first mathematical model comprises environmental data arranged in a first array of cells, and wherein the second mathematical model comprises environmental data arranged in a second array of cells.

3. The method according to claim 2 , wherein the array of cells correspond to a geolocation relative to the first autonomous vehicle or the second autonomous vehicle.

4. The method according to claim 2 , wherein merging the second mathematical model with the first mathematical model further comprises:
in the event a cell of the first array of cells is invalid, entering data from a corresponding cell of the second array of cells.

5. The method according to claim 2 , wherein merging the second mathematical model with the first mathematical model further comprises:
in the event a cell of the first array of cells is valid a corresponding cell of the second array of cells is valid, applying a weighted average to the cell of the first array of cells and the corresponding cell of the second array of cells.

6. The method according to claim 1 , wherein the environment data comprises data selected from the group consisting of terrain data, slippage data, georeferenced data, ego-centric data, and obstacle data.

7. The method according to claim 1 , wherein merging the second mathematical model with the first mathematical model further comprises:
applying a weighted average to the data in the first mathematical model and the second mathematical model.

8. The method according to claim 1 , wherein sending a request for additional environmental data to a second autonomous vehicle includes geolocation data.

9. The method according to claim 1 , wherein sending a request for additional environmental data to a second autonomous vehicle includes an indication specifying the type of environmental data.

10. The method according to claim 1 , further comprising:
receiving a third mathematical model from a third autonomous vehicle; and
merging the third mathematical model with the first mathematical model and the second mathematical model.

11. The method according to claim 1 , wherein the merging the second mathematical model with the first mathematical model comprises replacing the first mathematical model with the second mathematical model.

12. An autonomous vehicle comprising:
a sensor;
a transceiver; and
a control system comprising a plurality of distinct control systems and a controller in communication with the sensor and the transceiver, wherein the controller:
receives first environmental data representing the environment near the autonomous vehicle from the sensor;
creates a first mathematical model representing the environment near the autonomous vehicle based on the first environmental data;
sends a request for additional environmental data to a second autonomous vehicle via the transceiver;
receives a second mathematical model from the second autonomous vehicle via the transceiver;
merges the second mathematical model with the first mathematical model;
shares the merged mathematical model with a group of autonomous vehicles, wherein the group of autonomous vehicles comprises at least the first autonomous vehicle and the second autonomous vehicle; and
controls the group of autonomous vehicles based on the merged mathematical model by increasing control horizon of the group of autonomous vehicles.

13. The autonomous vehicle according to claim 12 , wherein the first mathematical model comprises environmental data arranged in a first array of cells, and wherein the second mathematical model comprises environmental data arranged in a second array of cells.

14. The autonomous vehicle according to claim 13 , wherein the array of cells correspond to a geolocation relative to the first autonomous vehicle or the second autonomous vehicle.

15. The autonomous vehicle according to claim 13 , wherein merging the second mathematical model with the first mathematical model further comprises:
in the event a cell of the first array of cells is invalid, entering data from a corresponding cell of the second array of cells.

16. The autonomous vehicle according to claim 13 , wherein merging the second mathematical model with the first mathematical model further comprises:
in the event a cell of the first array of cells is valid a corresponding cell of the second array of cells is valid, applying a weighted average to the cell of the first array of cells and the corresponding cell of the second array of cells.

17. The autonomous vehicle according to claim 12 , wherein the environment data comprises data selected from the group consisting of terrain data, slippage data, georeferenced data, ego-centric data, and obstacle data.

18. The autonomous vehicle according to claim 12 , wherein merging the second mathematical model with the first mathematical model further comprises:
applying a weighted average to the data in the first mathematical model and the second mathematical model.

19. The autonomous vehicle according to claim 12 , wherein the controller:
receives a third mathematical model from a third autonomous vehicle via the transceiver; and
merges the third mathematical model with the first mathematical model and the second mathematical model.

20. The autonomous vehicle according to claim 12 , further comprising a geolocation sensor, and wherein the request for additional environmental data includes geolocation data from the geolocation sensor.

21. The autonomous vehicle according to claim 13 , wherein merging the second mathematical model with the first mathematical model comprises replacing the first mathematical model with the second mathematical model.

22. A non-transitory, tangible computer readable medium communicatively coupled to the one or more processors and storing executable instructions executable by the one or more processors to perform:
sensing an environment, via a sensor, near a first autonomous vehicle to produce first environmental data;
creating a first mathematical model representing the environment near the first autonomous vehicle based on the first environmental data;
sending a request for additional environmental data to a second autonomous vehicle;
receiving a second mathematical model from the second autonomous vehicle;
merging the second mathematical model with the first mathematical model;
sharing the merged mathematical model with a group of autonomous vehicles, wherein the group of autonomous vehicles comprises at least the first

Assignees

• Autonomous Solutions Inc

Inventors

• Ferrin Jeff
• Bybee Taylor
• Bunderson Nate

Classifications

• G01C21/3461

  Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries · CPC title

• G01C21/3841

  Data obtained from two or more sources, e.g. probe vehicles · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G08G1/0112 Primary

  from the vehicle, e.g. floating car data [FCD] · CPC title