Method and apparatus for the classification of data

• US 8,897,997 B2
• Filed: 05/09/2012
• Issued: 11/25/2014
• Est. Priority Date: 05/12/2011
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Firl, Jonas, Stuebing, Hagen
• Primary Examiner(s): Cheung, Calvin
• Assistant Examiner(s): Martinez Borrero, Luis A
• Application Number:
  US13/467,109
• Publication Number:
  US 20120290198A1
• Time in Patent Office: 930 Days
• Field of Search: 701/29, 701/210, 701/213, 701/27, 701/117, 701/209, 701/2, 701/33, 701/50, 701/201, 701/414, 701/36, 701/45, 701/22, 701/70, 701/29.3, 701/31.5, 701/49, 701/96, 701/23, 701/24, 701/102, 701/118, 701/110, 455/426.1, 370/338, 463/1, 711/154, 340/989, 340/466, 340/474, 340/905, 340/870, 343/703, 343/894
• US Class Current: 701/117
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/07 Controlling traffic signals
• CPC Class Codes: G08G 1/163 involving continuous checking
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: H04W 4/024 Guidance services
• CPC Class Codes: H04W 4/46 for vehicle-to-vehicle communication [V2V]

Abstract

A method for the classification of data includes receiving a first message that is a vehicle-to-vehicle or a vehicle-to-infrastructure message. The first message includes first mobility data of a vehicle. An expected route of the vehicle is determined based on the first mobility data. A second message that is a vehicle-to-vehicle or a vehicle-to-infrastructure message is received. The second message includes second mobility data of the vehicle. An actual route of the vehicle is determined based on the second mobility data. Whether the expected route deviates from the actual route by at least a predetermined threshold value is determined. If the expected route deviates from the actual route by at least the predetermined threshold value, a type of momentary driving maneuver of the vehicle is determined and the first mobility data and the second mobility data are classified on the basis of the type of momentary driving maneuver.

Claims

1. A method for classification of data, the method comprising the steps of:

receiving, at a first vehicle, a first message from a second vehicle that is a vehicle-to-vehicle message and a vehicle-to-infrastructure message, wherein the first message includes first mobility data of the second vehicle;

determining, with a computing unit of the first vehicle, an expected route of the second vehicle based on the first mobility data;

receiving, at the first vehicle, a second message from the second vehicle that is a vehicle-to-vehicle message or a vehicle-to-infrastructure message, wherein the second message includes second mobility data of the second vehicle;

determining, with the computing unit of the first vehicle, an actual route of the second vehicle based on the second mobility data;

determining, with the computing unit of the first vehicle, whether the expected route deviates from the actual route by at least a predetermined threshold value, wherein determining the type of momentary driving maneuver of the second vehicle is performed on a basis of the first mobility data and the second mobility data, and

if determined that the expected route deviates from the actual route by at least the predetermined threshold value, determining, with the computing unit of the first vehicle, a type of momentary driving maneuver of the second vehicle and classifying the first mobility data and the second mobility data on a basis of the type of momentary driving maneuver,

wherein classifying the first mobility data and the second mobility data comprises the steps of;

adapting the predetermined threshold value to an adapted threshold value based on the type of momentary driving maneuver; and

determining whether the expected route deviates from the actual route by at least the adapted threshold value, and

wherein, if it is determined that the expected route deviates from the actual route by at least the adapted threshold value, the first mobility data and the second mobility data are classified as being erroneous, and wherein if it is determined that the expected route does not deviate from the actual route by at least the adapted threshold value, the first mobility data and the second mobility data are classified as being free from errors.

2. The method according to claim 1, wherein determining the type of momentary driving maneuver of the second vehicle is performed on a basis of a Hidden Markov model.

3. The method according to claim 1, wherein determining the type of momentary driving maneuver of the second vehicle is performed on a basis of a Kalman filter method.

4. The method according to claim 1, wherein, if it is determined that the expected route does not deviate from the actual route by at least the adapted threshold value, adaptation of a Kalman Gain value is performed.

5. The method according to claim 1, wherein determining the actual route of the second vehicle and/or determining the type of momentary driving maneuver of the second vehicle is performed additionally on a basis of data determined from a sensor, wherein the sensor is an electromagnetic sensor, an acoustic sensor, or an optical camera.

6. The method according to claim 1, wherein the first message and/or the second message are part of periodically sent messages.

7. The method according to claim 1, wherein at least after receiving the first message a plausibility check on the first mobility data is performed and wherein determining the expected route, determining the actual route and determining whether the expected route deviates from the actual route by at least the predetermined threshold value is performed, if the first mobility data are determined as being plausible.

8. The method according to claim 1, wherein the first message additionally includes an identifier of a transmitting device sending the first message and wherein determining the expected route, determining the actual route and determining whether the expected route deviates from the actual route by at least the predetermined threshold value are performed if a further message has already been received from the transmitting device.

9. The method according to claim 1, wherein the first mobility data and/or the second mobility data, after classifying, are communicated to a driver assistance system and/or an infrastructure facility.

10. A non-transitory computer readable medium embodying a computer program product, the computer program product comprising:

a program to classify data, the program configured to;

receive a first message at a first vehicle that is a vehicle-to-vehicle message and a vehicle-to-infrastructure message from a second vehicle, wherein the first message includes first mobility data of the second vehicle;

determine at the first vehicle an expected route of the second vehicle based on the first mobility data;

receive at the first vehicle a second message that is a vehicle-to-vehicle message or a vehicle-to-infrastructure message, wherein the second message includes second mobility data of the second vehicle;

determine at the first vehicle an actual route of the second vehicle based on the second mobility data;

determine at the first vehicle whether the expected route of the second vehicle deviates from the actual route by at least a predetermined threshold value, and

if determined that the expected route deviates from the actual route by at least the predetermined threshold value, determine a type of momentary driving maneuver of the second vehicle and classifying the first mobility data and the second mobility data on a basis of the type of momentary driving maneuver.