Vehicle passenger identification

Patent metadata

Field	Value
Publication number	US-9823081-B2
Application number	US-201414559136-A
Country	US
Kind code	B2
Filing date	Dec 3, 2014
Priority date	Dec 3, 2014
Publication date	Nov 21, 2017
Grant date	Nov 21, 2017

Abstract

At least one first model represents a person. A request to pick up a passenger includes a first location and a personal identifier for the passenger. A vehicle is caused to navigate to the first location. The passenger is identified by comparing a second model generated from vehicle sensor data with the first model.

First claim

The invention claimed is:

1. A system, comprising a computer for installation in an autonomous vehicle, the computer comprising a processor and a memory, the memory storing instructions executable by the processor to:
store at least one first model that includes lidar data representing a particular human person;
receive a request to pick up a passenger, the request including a first location that is a passenger pickup location;
cause the vehicle to navigate to the first location;
identify the passenger as the particular human person represented in the first data model by comparing a second model that includes lidar data generated from vehicle sensor data with the first model that includes lidar data; and
cause the vehicle to navigate from the first location that is the passenger pickup location to a second location that is determined according to the second model to be a more precise location of the passenger than the first location.

2. The system of claim 1 , wherein the computer is further programmed to cause the vehicle to provide the passenger with access to the vehicle upon identifying the passenger.

3. The system of claim 1 , wherein the first model further data includes image data.

4. The system of claim 3 , wherein the vehicle sensor data includes image data.

5. The system of claim 1 , wherein the at least one first model is a plurality of first models.

6. The system of claim 5 , wherein the computer is further programmed to score each of the first models based on the comparison to the second model, and to identify the passenger according to a highest scoring first model.

7. The system of claim 6 , wherein the computer is further programmed to identify the passenger only if the highest scoring first model matches the second model within a predetermined degree of confidence.

8. The system of claim 1 , wherein the computer is further programmed to retrieve at least one first model from a remote device.

9. The system of claim 1 , wherein at least one first model is provided with the request.

10. A method performed by an autonomous vehicle, comprising:
storing at least one first model that includes lidar data representing a particular human person;
receiving a request to pick up a passenger, the request including a first location that is a passenger pickup location;
causing the vehicle to navigate to the first location;
identifying the passenger as the particular human person represented in the first data model by comparing a second model that includes lidar data generated from vehicle sensor data with the first model that includes lidar data; and
navigating from the first location that is the passenger pickup location that to a second location that is determined according to the second model to be a more precise location of the passenger than the first location.

11. The method of claim 10 , further comprising providing the passenger with access to the vehicle upon identifying the passenger.

12. The method of claim 10 , wherein the first model further data includes image data.

13. The method of claim 12 , wherein the vehicle sensor data includes image data.

14. The method of claim 10 , wherein the at least one first model is a plurality of first models.

15. The method of claim 14 , further comprising scoring each of the first models based on the comparison to the second model, and identifying the passenger according to a highest scoring first model.

16. The method of claim 15 , further comprising identifying the passenger only if the highest scoring first model matches the second model within a predetermined degree of confidence.

17. The method of claim 10 , further comprising retrieving at least one first model from a remote device.

18. The method of claim 10 , wherein at least one first model is provided with the request.

Assignees

• Ford Global Tech Llc

Inventors

• Crawford Mark
• Mcbride James Robert
• Elwart Shane
• Cohen Schuyler

Classifications

• G06Q10/047 Primary

  Optimisation of routes or paths, e.g. travelling salesman problem · CPC title

• G01C21/34 Primary

  Route searching; Route guidance · CPC title

• G01S17/89 Primary

  for mapping or imaging · CPC title

• B60R25/25

  using biometry · CPC title

• G08G1/202 Primary

  Dispatching vehicles on the basis of a location, e.g. taxi dispatching · CPC title