Learning method and learning device for switching modes of autonomous vehicle based on on-device standalone prediction to thereby achieve safety of autonomous driving, and testing method and testing device using the same

Abstract

A learning method for generating parameters capable of representing a degree of credibility of an object detection during a process of the object detection is provided. And the method includes steps of: (a) a learning device instructing a convolutional layer to generate a convolutional feature map by applying a convolutional operation to a training image; (b) the learning device instructing an anchor layer to generate an RPN confidence map including RPN confidence scores; (c) the learning device instructing an FC layer to generate CNN confidence scores, to thereby generate a CNN confidence map; and (d) the learning device instructing a loss layer to learn parameters in the CNN and the RPN by performing backpropagation using an RPN loss and a CNN loss, generated by referring to the RPN confidence map, the CNN confidence map, an estimated object detection result and a GT object detection result.

Description

CROSS REFERENCE OF RELATED APPLICATION[0001]This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 798,676, filed Jan. 30, 2019, the entire contents of which are incorporated herein by reference.FIELD OF THE DISCLOSURE[0002]The present disclosure relates to a learning method and a learning device for use with an autonomous vehicle; and more particularly, to the learning method and the learning device for switching modes of an autonomous vehicle based on an on-device standalone prediction to thereby achieve safety of an autonomous driving, and a testing method and a testing device using the same.BACKGROUND OF THE DISCLOSURE[0003]Recently, an autonomous driving technology has been studied, so that an autonomous vehicle could be driven with a fairly high accuracy without an intervention of a driver. However, such autonomous driving technology may not work well in certain situations. For example, in case of a camera-based autonomous vehicle, if a f...

AI Technical Summary

Benefits of technology

[0007]It is an object of the present disclosure to provide a learning method for switching modes of an autonomous vehicle based on an on-device standalone prediction, to thereby achieve a safety of an autonomous driving.

[0008]It is another object of the present disclosure to provide a method for generating parameters capable of representing a degree of credibility of an object detection during a process of the object detection.

Problems solved by technology

However, such autonomous driving technology may not work well in certain situations.

For example, in case of a camera-based autonomous vehicle, if a field of view of a camera installed on the autonomous vehicle suddenly becomes dark, images acquired by the camera may not be appropriate for an autonomous driving, therefore the camera-based autonomous vehicle may not work properly.

For example, in case a weather is extremely bad or a street light is broken at night, whether the vehicle should be driven autonomously or not cannot be determined properly by using a passively updated database like the geographic zones database.

That is, a problem of the prior art is that it is difficult to deal with such a case.

Images