← USPTO Patent Grants

Training of a convolutional neural network

Grant US12579442B2 Kind: B2 Mar 17, 2026

Assignee

Elektrobit Automotive GmbH

Inventors

Sorin Mihai Grigorescu, Bogdan Trasnea, Andrei Vasilcoi

Abstract

This disclosure is related to a method, a computer program code, and an apparatus for training a convolutional neural network for an autonomous driving system. The disclosure is further related to a convolutional neural network, to an autonomous driving system comprising a neural network, and to an autonomous or semi-autonomous vehicle comprising such an autonomous driving system. For training the convolutional neural network, in a first step real-world driving data are selected as training data. Furthermore, synthetic driving data are generated as training data. The convolutional neural network is then trained on the selected real-world driving data and the generated synthetic driving data using a genetic algorithm.

CPC Classifications

G06N 3/086 B60W 60/0027 B60W 2050/0018 G06V 10/774 G08G 1/0125

Filing Date

2020-06-17

Application No.

17626575

Claims

14