Inter-vehicle sensor validation using senso-fusion network

Patent metadata

Field	Value
Publication number	US-11260876-B2
Application number	US-201816180183-A
Country	US
Kind code	B2
Filing date	Nov 5, 2018
Priority date	Nov 5, 2018
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

A system and method of sensor validation utilizing a sensor-fusion network. The sensor-fusion network may comprise a number of sensors associated with one or more vehicles having autonomous or partially autonomous driving functions.

First claim

What is claimed is:

1. An vehicle-sensor validation system comprising:
a coordinating processor operable for data communication with a number of vehicles;
a sensor-fusion network comprising a plurality of sensors each in data communication with the coordinating processor and a plurality of location sensors each operable to indicate a position of one of the plurality of sensors, the sensor-fusion network comprising at least a first sensor operable to generate first data, a second sensor operable to generate second data, and a third sensor operable to generate third data,
wherein the first sensor is associated with a first vehicle of the number of vehicles, the first data indicates a first detection status of an object, the second data indicates a second detection status of the object, the third data indicates a third detection status of the object, and wherein the coordinating processor is operable to generate coordinated data based upon the first data, second data, third data, and the relative positions of the second sensor and third sensor with respect to first sensor, the coordinated data comprising a weighted detection status of the object and generated using a majority-voting algorithm, and wherein the coordinating processor is operable to transition a sensor indicating the minority result of the majority-voting algorithm into a safe state mode.

2. The system of claim 1 , wherein the second sensor is associated with the first vehicle and the third sensor is associated with a second vehicle of the number of vehicles.

3. The system of claim 1 , wherein the first data comprises a first confidence value, the second data comprises a second confidence value, and the third data comprises a third confidence value, the weighted detection status being generated using the first confidence value, second confidence value, and third confidence value as weights.

4. The system of claim 1 , wherein the majority-voting algorithm is a 2-out-of-3 algorithm using the first data, second data, and third data as inputs.

5. The system of claim 1 , wherein the second sensor is associated with a second vehicle of the number of vehicles and the third sensor is associated with a third vehicle of the number of vehicles.

6. The system of claim 1 , wherein the coordinating processor comprises a neural network operable to identify whether a potential trajectory of the first vehicle is free of obstacles.

7. The system of claim 1 , wherein the coordinating processor is operable to dynamically define the sensor-fusion network as a subset of the plurality of sensors according to proximity of each of the plurality of sensors to the first vehicle.

8. The system of claim 1 , wherein the coordinating processor is operable to detect a fault condition in the first sensor.

9. The system of claim 1 , wherein each sensor of the plurality of sensors in the sensor-fusion network comprises a specified accuracy and the coordinating processor is operable to dynamically define the sensor-fusion network as a subset of the plurality of sensors based upon the specified accuracy of each sensor.

10. The system of claim 9 , wherein coordinating processor is operable to select sensors for inclusion in sensor-fusion network based upon a minimum specified accuracy.

11. The system of claim 1 , wherein the first sensor comprises a sensor type select from one of a group of sensor types including a radar sensor, lidar sensor, proximity sensor, camera sensor, infrared sensor, ultraviolet sensor, ultrasonic sensor, or sonic sensor.

12. The system of 11 , wherein the second sensor comprises a different sensor type from the first sensor.

13. The system of claim 8 , the fault condition comprising one of a bit flip, a software error, or an incorrect sensor scheduling of the first sensor.

Assignees

• Bosch Gmbh Robert

Inventors

• Schwindt Oliver
• Heyl Andreas
• Gussner Thomas
• Kienle Theresa
• Mueller Joachim
• Reuter Stephan

Classifications

• B60W2050/0215

  Sensor drifts or sensor failures · CPC title

• B60W50/04 Primary

  Monitoring the functioning of the control system · CPC title

• B60W2556/65

  Data transmitted between vehicles · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W2050/046

  involving external transmission of data to or from the vehicle, e.g. via telemetry, satellite, Global Positioning System [GPS] · CPC title