KR-20260066940-A - APPARATUS FOR PREDICTING DRIVING INFORMATION OF VEHICLE, METHOD FOR LEARNING ARTIFICIAL NEURAL NETWORK FOR PREDICTING DRIVING INFORMATION

Abstract

The present invention relates to a method for training an artificial neural network for predicting driving information of a driving information prediction device connected to a VILS (vehicle in the loop simulation) system, comprising: a step of obtaining VILS driving data and actual driving data of a vehicle from the VILS system; a step of refining the VILS driving data and the actual driving data and converting the VILS driving data and the actual driving data into training data based on the refining; and a step of training the artificial neural network to output a driving information prediction result of the vehicle using the training data as input.

Inventors

• 이충희
• 배재우

Assignees

• 이인텔리전스 주식회사

Dates

Publication Date

20260512

Application Date

20241105

Claims (1)

1. A method for training an artificial neural network for driving information prediction of a driving information prediction device connected to a VILS (vehicle in the loop simulation) system, A step of obtaining VILS driving data and actual driving data of the vehicle from the above VILS system; A step of refining the VILS driving data and the actual driving data, and converting the VILS driving data and the actual driving data into training data based on the refinement; and A step of training the artificial neural network to output a driving information prediction result of the vehicle using the training data as input; A method for training an artificial neural network to predict vehicle driving information.

Description

Apparatus for Predicting Driving Information of Vehicle, Method for Learning Artificial Neural Network for Predicting Driving Information The present invention relates to a technology for predicting vehicle driving information. In the development of vehicles, verifying safety standards for new vehicles has traditionally relied primarily on testing on actual roads; however, this approach is not only highly inefficient in terms of time and cost but also entails safety issues. In particular, for advanced systems such as autonomous driving technology, it is practically impossible to test every potential on real roads. Consequently, there is a growing need for more efficient and safer testing methods. Against this backdrop, Vehicle in the Loop (VILS) systems are gaining prominence for vehicle development. VILS is a technology that combines a real vehicle with a virtual simulation environment to reproduce and test various driving situations. It helps review diverse scenarios from the early stages of development, identify potential issues in advance, and optimize system performance. However, it is necessary to verify whether the VILS system's test results are comparable to those of a real target. The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as publicly known technology disclosed to the general public prior to the filing of the present invention. FIG. 1 is a block diagram illustrating the function of a driving information providing system including a driving information prediction device for a vehicle according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating the function of a vehicle driving information prediction device according to an embodiment of the present invention. FIG. 3 is a block diagram that exemplarily explains the function of an artificial neural network included in the storage unit of the driving information prediction device of FIG. 2. FIG. 4 is a flowchart illustrating an exemplary method of training an artificial neural network to predict driving information of a vehicle according to an embodiment of the present invention. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the scope of the present invention is defined only by the claims. In describing the embodiments of the present invention, specific descriptions of known functions or configurations will be omitted unless actually necessary for describing the embodiments of the present invention. Furthermore, the terms described below are defined in consideration of the functions in the embodiments of the present invention, and these may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. VILS is a technology that combines actual vehicles with virtual simulation environments to reproduce and test various driving situations. It helps review diverse scenarios from the early stages of development, identify potential issues in advance, and optimize system performance. However, it is necessary to verify whether the test results for the VILS system are similar to those of a real target. Accordingly, in an embodiment of the present invention, we propose a vehicle driving information prediction technology that provides more accurate and reliable test results by analyzing the test results of a VILS system and the actual target records using artificial intelligence, and by developing an AI model capable of similarly predicting actual driving results based on the test results of VILS. Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. FIG. 1 is a block diagram illustrating the function of a driving information providing system (1) including a driving information prediction device (100) of a vehicle according to an embodiment of the present invention. As illustrated in FIG. 1, the driving information providing system (1) may include a VILS system (10) and a driving information prediction device (100). The VILS system (10) performs the function of reproducing and testing various driving situations by combining a real vehicle and a virtual simulation environment. The VILS system (10) can review various scenarios from the early stages of development, identify potential problems in advance, and optimize the performance