干旱区生态环境知识资源中心(Arid): A New Open-Source Off-Road Environment for Benchmark Generalization of Autonomous Driving

Arid

DOI	10.1109/ACCESS.2021.3116710
	A New Open-Source Off-Road Environment for Benchmark Generalization of Autonomous Driving
	Han, Isaac; Park, Dong-Hyeok; Kim, Kyung-Joong
通讯作者	Kim, KJ (corresponding author), Gwangju Inst Sci & Technol, Sch Integrated Technol, Gwangju 61005, South Korea.
来源期刊	IEEE ACCESS
ISSN	2169-3536
出版年	2021
卷号	9 页码:136071-136082
英文摘要	Recently, deep neural networks have greatly improved autonomous driving. However, as a great deal of training data is required, most studies have employed simulators. Generalization of such driving is key in terms of safety. The simulated environments feature only small variations in favorable conditions and thus cannot be used for benchmarking. Therefore, we developed a new open-source (OpenAI Gym-like) off-road environment featuring differently structured forests, plateaus, deserts, and snowfields. The dynamic topographical structures make the off-road environment a very challenging generalization problem. Our off-road environment can precisely evaluate autonomous driving in terms of generalization. Additionally, we proposed an evaluation method based on the success rate of driving tasks, enabling effective driving ability measurement. Furthermore, we evaluate the performance of existing end-to-end driving methods in our off-road environment. The results show that the end-to-end driving methods lack generalization ability and fail to generalize to unseen environments. Our off-road environment can help autonomous driving researchers develop a better, generalizable driving system. Unreal engine-level assets and codes are available at https://github.com/lssac7778/Off-road-Benchmark. We briefly introduce our model in https://www.youtube.com/watch?v=SERSv0TFUwQ&t=44s.
英文关键词	Autonomous vehicles Benchmark testing Roads Open source software Training Visualization Urban areas Generalization autonomous driving reinforcement learning off-road environments imitation learning
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000704817200001
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS研究方向	Computer Science ; Engineering ; Telecommunications
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/363553
作者单位	[Han, Isaac; Park, Dong-Hyeok; Kim, Kyung-Joong] Gwangju Inst Sci & Technol, Sch Integrated Technol, Gwangju 61005, South Korea
推荐引用方式 GB/T 7714	Han, Isaac,Park, Dong-Hyeok,Kim, Kyung-Joong. A New Open-Source Off-Road Environment for Benchmark Generalization of Autonomous Driving[J],2021,9:136071-136082.
APA	Han, Isaac,Park, Dong-Hyeok,&Kim, Kyung-Joong.(2021).A New Open-Source Off-Road Environment for Benchmark Generalization of Autonomous Driving.IEEE ACCESS,9,136071-136082.
MLA	Han, Isaac,et al."A New Open-Source Off-Road Environment for Benchmark Generalization of Autonomous Driving".IEEE ACCESS 9(2021):136071-136082.