一句话：提出面向车辆仿真的迁移学习方法，将真实驾驶数据中的汽车行为迁移到仿真器，并在 CARLA 中验证其效果与运行时效率。
在仿真应用中生成可信且实时的车辆行为一直困难：既要真实可信，又要运行高效，且手工实现行为模型会显著增加开发成本。本文提出一种自动化的车辆仿真系统设计方法，利用先进深度学习技术和自动驾驶领域常用数据集，将从真实世界学到的车辆行为迁移到仿真器。该方法旨在降低手工建模成本，并支持资源受限场景下的运行时评估。作者在 CARLA 仿真器上开展实验，从定量和定性两方面评估迁移效果。结果表明，该迁移学习方案效果良好，并且即使在视频游戏等资源受限的仿真应用中也可用于运行时评估。
Creating synthetic behaviors of vehicles in simulation applications has always been challenging from a development standpoint. First, it is a real challenge to create a credible and realistic simulation while achieving the required runtime efficiency. Second, the effort required to implement it can add significant cost to the development processes. In this paper, we propose an automated way to design vehicle simulation systems by transfer learning from reality to simulators. Our methods rely on advanced deep learning technologies and datasets commonly used in the field of self-driving cars. To assess how well this approach would work in a simulation environment, experiments using the CARLA simulator are presented in the evaluation. The results show that the proposed transfer learning approach provides good results, both quantitatively and qualitatively, and is suitable for runtime evaluation even in resource-constrained simulation applications such as video games.
DOI 原文 ·
@inproceedings{paperbot7195,
title = {Transfer learning of cars behaviors from reality to simulation applications},
author = {Ciprian Paduraru and Miruna Gabriela Paduraru and Andrei Blahovici},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3560506}
}