Enhanced image preprocessing method for an autonomous vehicle agent system

Computer Science and Information Systems

article

Kaisi Huang¹  Mingyun Wen¹  Jisun Park¹  Yunsick Sung¹  Jong Hyuk Park²  Kyungeun Cho¹ 

[1] Department of Multimedia Engineering, Dongguk University-Seoul;Department of Computer Science and Engineering, Seoul National University of Science and Technology

关键词: Image preprocessing;    Reinforcement learning;    Deep Q learning;   

DOI  :  10.2298/CSIS200212005H

学科分类：土木及结构工程学

来源: Computer Science and Information Systems

【 摘 要 】

Excessive training time is a major issue face when training autonomous vehicle agents with neural networks by using images as input. This paper proposes a deep time-economical Q network (DQN) input image preprocessing method to train an autonomous vehicle agent in a virtual environment. The environmental information is extracted from the virtual environment. A top-view image of the entire environment is then redrawn according to the environmental information. During training of the DQN model, the top-view image is cropped to place the vehicle agent at the center of the cropped image. The current frame top-view image is combined with the images from the previous two training iterations. The DQN model use this combined image as input. The experimental results indicate higher performance and shorter training time for the DQN model trained with the preprocessed images compared with that trained without preprocessing.

【 授权许可】

CC BY-NC-ND