Recognizing authorized vehicle user with movement data

Patent metadata

Field	Value
Publication number	US-11052874-B2
Application number	US-201916721290-A
Country	US
Kind code	B2
Filing date	Dec 19, 2019
Priority date	Dec 21, 2018
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

Abstract

The invention relates to a method for authenticating a vehicle user. In the method, movement data of a sensor identification circuit are detected by sensors. The detected movement data are supplied to a self-learning system. The self-learning system ascertains a movement profile based on the supplied movement data and assigns this to a vehicle user. Upon approach of the vehicle by a vehicle user, it is checked whether movement data detected at the point in time of the approach corresponds to a movement profile, which is assigned to a vehicle user authorized to use the vehicle. In the event of a match, the vehicle user approaching the vehicle is authorized to use the vehicle.

First claim

What is claimed is:

1. A method for authenticating a vehicle user with the aid of the movement data, comprising:
receiving a movement profile for the vehicle user, wherein the movement profile comprises fused sensor data from a plurality of different sensor data associated with multiple layers of linked artificial neurons and vectors characterizing movements of the vehicle user;
detecting the vehicle user's approach to a vehicle;
obtaining movement data from the detected user's approach to the vehicle;
determining that the movement data detected corresponds to the received movement profile; and
authorizing at least one function of the vehicle for use by the approaching vehicle user.

2. The method according to claim 1 , wherein determining that the movement data corresponds to a movement profile is performed after leaving and/or after approaching the vehicle before opening the vehicle.

3. The method according to claim 1 , wherein the fused sensor data comprises sensed data in an immediate vicinity of the vehicle and outside the immediate vicinity.

4. The method according to claim 3 , further comprising: detecting a distance and/or position of the vehicle user relative to the vehicle in the immediate vicinity of the vehicle, the detecting being detected by a propagation time measurement between at least one radio component integrated in the vehicle.

5. The method according to claim 4 , wherein the radio components comprise ultra-wideband components (UWB).

6. The method according to claim 1 , wherein the plurality of different sensor data comprises sensor data from at least two of acceleration sensors, gyro sensors, magnetic sensors, and combination thereof.

7. The method according to claim 1 , wherein the fused sensor data comprises movement data divided into successive time samples.

8. The method according to claim 7 , wherein the fused sensor data comprises a movement sequence of the vehicle user with respect to a location in the immediate vicinity of the vehicle.

9. The method according to claim 8 , wherein determining that the movement data detected corresponds to the received movement profile comprises determining that movement data detected at the point in time of the approach correspond to a movement sequence.

10. A system for authenticating a vehicle user with the aid of the movement data, comprising:
a processing apparatus;
a vehicle sensor identification circuit, operatively coupled to the processing apparatus; and
a memory for receiving a movement profile for the vehicle user, wherein the movement profile comprises fused sensor data from a plurality of different sensor data associated with multiple layers of linked artificial neurons and vectors characterizing movements of the vehicle user, wherein the processing apparatus, the vehicle sensor identification circuit and the memory are configured to
detect the vehicle user's approach to the vehicle;
obtain movement data from the detected user's approach to the vehicle;
determine that the movement data detected corresponds to the received movement profile; and
authorize at least one function of the vehicle for use by the approaching vehicle user.

11. The system according to claim 10 , wherein the vehicle sensor identification circuit and the memory are configured to determine that the movement data corresponds to a movement profile is performed after leaving and/or after approaching the vehicle before opening the vehicle.

12. The system according to claim 10 , wherein the fused sensor data comprises sensed data in an immediate vicinity of the vehicle and outside the immediate vicinity.

13. The system according to claim 12 , wherein the vehicle sensor identification circuit and the memory are configured to detect a distance and/or position of the vehicle user relative to the vehicle in the immediate vicinity of the vehicle, the detecting being detected by a propagation time measurement between at least one radio component integrated in the vehicle.

14. The system according to claim 13 , wherein the radio components comprise ultra-wideband components (UWB).

15. The system according to claim 10 , wherein the plurality of different sensor data comprises sensor data from at least two of acceleration sensors, gyro sensors, magnetic sensors, and combination thereof.

16. The system according to claim 10 , wherein the fused sensor data comprises movement data divided into successive time samples.

17. The system according to claim 16 , wherein the fused sensor data comprises a movement sequence of the vehicle user with respect to a location in the immediate vicinity of the vehicle.

18. The system according to claim 17 , wherein the vehicle sensor identification circuit and the memory are configured to determine that the movement data detected corresponds to the received movement profile by determining that movement data detected at the point in time of the approach correspond to a movement sequence.

19. A method for authenticating a vehicle user for a vehicle with the aid of the movement data, comprising:
receiving a movement profile for the vehicle user, wherein the movement profile comprises fused sensor data from a plurality of different sensor data associated with multiple layers of linked artificial neurons and vectors characterizing movements of the vehicle user, and wherein the fused sensor data comprises time-adjusted sensor data based on characterized movements along successive time samples;
detecting the vehicle user's approach to the vehicle using a propagation time measurement between at least one radio component integrated in the vehicle;
obtaining movement data from the detected user's approach to the vehicle;
determining that the movement data detected corresponds to the received movement profile; and
authorizing at least one function of the vehicle for use by the approaching vehicle user.

20. The method according to claim 19 , wherein the plurality of different sensor data comprises sensor data from at least two of acceleration sensors, gyro sensors, magnetic sensors, and combination thereof.

Assignees

• Volkswagen Ag

Inventors

• Ette Bernd

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/091

  Active learning · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/08

  Learning methods · CPC title