Estimating a Street Type Using Sensor-Based Surroundings Data

• US 20150211867A1
• Filed: 04/08/2015
• Published: 07/30/2015
• Est. Priority Date: 10/09/2012
• Status: Active Grant

• Current Assignee: Bayerische Motoren Werke AG
• Original Assignee: Bayerische Motoren Werke AG
• Inventors: NAGY, Istvan
• Granted Patent: US 10,072,936 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2552/05 Type of road, e.g. motorways, local streets, paved or unpaved roads
• CPC Class Codes: B60W 50/00 Details of control systems for road vehicle drive control not related to the control of a particular sub-unit , e.g. process diagnostic or vehicle driver interfaces
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G06F 18/25 Fusion techniques
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

A method for assessing a road type is carried out by an electronic computation apparatus. The method includes the steps of: reception of environment data based on a sensor measurement; assessment of the road type using a decision tree based on the environment data; assessment of the road type using a state machine based on the environment data; and formation of an overall assessment of the road type based on the assessment using the decision tree and the assessment using the state machine.

Claims

1. A method for assessing a road type on which a vehicle travels, the method comprising the acts of:

receiving, by an electronic computing apparatus, environment data based on a sensor measurement;

assessing, in the electronic computing apparatus, the road type using a decision tree based on the received environment data;

assessing, in the electronic computing apparatus, the road type using a state machine based on the received environment data;

forming, in the electronic computing apparatus, an overall assessment of the road type based on the assessment using the decision tree and the assessment using the state machine; and

outputting, from the electronic computing apparatus, the overall assessment to a driver assistance function of the vehicle.

2. The method according to claim 1, wherein the assessment of the road type using the state machine also comprises an output assessment that the road type cannot be determined.

3. The method according to claim 2, wherein:

the forming of the overall assessment comprises a setting of the overall assessment to the assessment using the state machine when the assessment using the state machine does not output that the road type cannot be determined; and

the formation of the overall assessment further comprises a setting of the overall assessment to the assessment using the decision tree when the assessment using the state machine outputs that the road type cannot be determined.

4. The method according to claim 3, further comprising the act of:

allocating, by the electronic computing apparatus, a qualification value to the overall assessment formed, the qualification value being based on whether the overall assessment is based on the assessment using the state machine or the assessment using the decision tree.

5. The method according to claim 4, further comprising the acts of:

receiving, by the electronic computing apparatus, a set of environment data based on sensor measurements, wherein each element of the set has an assigned instant;

for each element of the set received, creating a partial assessment of the road type using the decision tree based on the respective element of the set; and

wherein the allocation of the qualification value is also additionally based on the number of partial assessments that match the overall assessment.

6. The method according to claim 1, further comprising the acts of:

receiving, by the electronic computing apparatus, a set of environment data based on sensor measurements, wherein each element of the set has an assigned instant;

wherein the assessing of the road type using the decision tree further comprises the acts of;

for each element of the set, creating a partial assessment of the road type using the decision tree based on the respective element of the set; and

assessing the road type based on the partial assessments created, wherein the assessment uses a majority decision.

7. The method according to claim 4, further comprising the acts of:

receiving, by the electronic computing apparatus, a set of environment data based on sensor measurements, wherein each element of the set has an assigned instant;

wherein the assessing of the road type using the decision tree further comprises the acts of;

for each element of the set, creating a partial assessment of the road type using the decision tree based on the respective element of the set; and

assessing the road type based on the partial assessments created, wherein the assessment uses a majority decision.

8. The method according to claim 1, wherein the decision tree is induced by machine learning.

9. The method according to claim 8, wherein the machine learning uses training data that, as a decision result, prescribe a determination of the road type using a satellite navigation system and a digital map.

10. The method according to claim 1, further comprising the act of:

determining a function parameter of a sensor based on the overall assessment formed of the road type.

11. The method according to claim 10, wherein the function parameter is an intensity of a power supply or a deactivation of the power supply.

12. An apparatus for assessing a road type on which a vehicle travels, comprising:

an electronic computing apparatus operatively configured to execute a program that;

receives, by an electronic computing apparatus, environment data based on a sensor measurement;

assesses, in the electronic computing apparatus, the road type using a decision tree based on the received environment data;

assesses, in the electronic computing apparatus, the road type using a state machine based on the received environment data;

forms, in the electronic computing apparatus, an overall assessment of the road type based on the assessment using the decision tree and the assessment using the state machine; and

outputs, from the electronic computing apparatus, the overall assessment to a driver assistance function of the vehicle.

13. A vehicle, comprising the apparatus according to claim 12.