Driving support method, data processor using the same, and driving support system using the same

1. A data processing device that estimates a driving behavior of a vehicle by using a driving behavior model, the driving behavior model indicating a relationship between a running state of the vehicle and the driving behavior, the driving behavior model being constructed based on a plurality of detection results indicating information about a plurality of objects which are outside of the vehicle and are detected by a sensor on the vehicle, the data processing device comprising:

a processor; and

a memory coupled to the processor, the memory storing a program that, when executed by the processor, causes the data processing device to:

acquire detected information including the detection results and indicating the running state of the vehicle or one or more conditions;

limit a predetermined selection range narrower than a range detectable by the sensor based on map information;

select, from the detection results included in the detected information acquired, one of the detection results that falls within the selection range; and

perform processing based on the one of the detection results selected.

2. The data processing device according to claim 1 ,

wherein the sensor is one of a plurality of sensors, and

wherein the program, when executed by the processor, causes the data processing device to:

acquire detected information from each of the plurality of sensors, the detected information including detection results of each of the plurality of sensors, and

select at least two of the detection results including one of the detection results of each of the plurality of sensors that is within the selection range.

3. The data processing device according to claim 1 ,

wherein the sensor is one of a plurality of sensors, and selection ranges including the selection range are predetermined for the plurality of sensors, respectively,

wherein the program, when executed by the processor, causes the data processing device to:

acquire detected information from each of the plurality of sensors, the detected information including detection results in each of the plurality of sensors,

make a sum set of the detection results by the plurality of sensors, and

use a sum range of the selection ranges, as the selection range.

4. The data processing device according to claim 1 ,

wherein the processing is learning processing that trains the driving behavior model, and

wherein the program, when executed by the processor, causes the data processing device to construct the driving behavior model by using an input parameter and supervised data indicating the driving behavior related to the running state, the input parameter being the one of the detection results selected and the supervised data.

5. The data processing device according to claim 1 ,

wherein the processing is estimation processing that estimates the driving behavior, and

wherein the program, when executed by the processor, causes the data processing device to input the one of the detection results selected as input data to the driving behavior model, and acquire output from the driving behavior model as the driving behavior.

6. The data processing device according to claim 1 ,

wherein the processing includes learning processing that trains the driving behavior model and estimation processing that estimates the driving behavior, and

wherein the program, when executed by the processor, causes the data processing device to:

when executing the learning processing, use the one of the detection results selected as an input parameter and construct the driving behavior model by using the input parameter and supervised data indicating the driving behavior related to the running state, and

when executing the estimation processing, input the one of the detection results selected as input data to the driving behavior model, and acquire output from the driving behavior model as the driving behavior.

7. The data processing device according to claim 1 , wherein the detection results indicate a distance to each of the objects detected by the sensor and a direction of the each of the objects by using the sensor as a starting point.

8. The data processing device according to claim 1 , wherein the processing based on the one of the detection results selected does not use the detection results other than the one of the detection results selected.

9. The data processing device according to claim 1 , wherein the program, when executed by the processor, causes the data processing device to acquire the selection range from a sensor profile.

10. The data processing device according to claim 9 , wherein the program, when executed by the processor, causes the data processing device to acquire the sensor profile from a storage device that is external to the data processing device.

11. The data processing device according to claim 9 , wherein the program, when executed by the processor, causes the data processing device to:

store the sensor profile, and

acquire the sensor profile from within the data processing device.

12. The data processing device according to claim 9 , wherein the sensor profile acquired includes distance information.

13. A driving support method that estimates a driving behavior of a vehicle by using a driving behavior model, the driving behavior model indicating a relationship between a running state of the vehicle and the driving behavior, the driving behavior model being constructed based on a plurality of detection results indicating information about a plurality of objects which are outside of the vehicle and are detected by a sensor included on the vehicle, the driving support method comprising:

inputting, to a computer, detected information including the detection results and indicating the running state of the vehicle or one or more conditions;

limiting a predetermined selection range narrower than a range detectable by the sensor based on map information;

selecting, from the detection results included in the input detected information, one of the detection results that falls within the selection range; and

performing processing based on the selected one of the detection results.

14. The driving support method according to claim 13 , wherein the processing based on the selected one of the detection results does not use the detection results other than the selected one of the detection results.

15. A driving support system, comprising:

a storage device which, in operation, stores a sensor profile; and

a data processing device that includes:

a processor; and

a memory coupled to the processor, the memory storing a program that, when executed by the processor, causes the data processing device to:

acquire a selection range from the sensor profile, the selection range being narrower than a range detectable by the sensor;

limit the selection range based on map information;

estimate a driving behavior of a vehicle by using a driving behavior model, the driving behavior model indicating a relationship between a running state of the vehicle and the driving behavior, the behavior model being constructed based on a plurality of detection results indicating information about a plurality of objects which are outside of the vehicle and are detected by a sensor included on the vehicle

acquire detected information including the detection results and indicating the running state of the vehicle or one or more conditions;

select, from the detection results included in the detected information acquired, one of the detection results that falls within the selection range; and

perform processing based on the one of the detection results selected, and

wherein the storage device is external to the data processing device.

16. The driving support system according to claim 15 , wherein the processing based on the one of the detection results selected does not use the detection results other than the one of the detection results selected.