Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving

doi:10.1109/TIV.2022.3225340

科研成果详情

题名	Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving
作者	Teng，Siyu 1,2; Chen，Long 3,4; Ai，Yunfeng 5; Zhou，Yuanye 6; Xuanyuan，Zhe 1; Hu，Xuemin 7
发表日期	2023
发表期刊	IEEE Transactions on Intelligent Vehicles
卷号	8 期号:1 页码:673-683
摘要	End-to-end autonomous driving provides a simple and efficient framework for autonomous driving systems, which can directly obtain control commands from raw perception data. However, it fails to address stability and interpretability problems in complex urban scenarios. In this paper, we construct a two-stage end-to-end autonomous driving model for complex urban scenarios, named HIIL (Hierarchical Interpretable Imitation Learning), which integrates interpretable BEV mask and steering angle to solve the problems shown above. In Stage One, we propose a pretrained Bird's Eye View (BEV) model which leverages a BEV mask to present an interpretation of the surrounding environment. In Stage Two, we construct an Interpretable Imitation Learning (IIL) model that fuses BEV latent feature from Stage One with an additional steering angle from Pure-Pursuit (PP) algorithm. In the HIIL model, visual information is converted to semantic images by the semantic segmentation network, and the semantic images are encoded to extract the BEV latent feature, which are decoded to predict BEV masks and fed to the IIL as perception data. In this way, the BEV latent feature bridges the BEV and IIL models. Visual information can be supplemented by the calculated steering angle for PP algorithm, speed vector, and location information, thus it could have better performance in complex and terrible scenarios. Our HIIL model meets an urgent requirement for interpretability and robustness of autonomous driving. We validate the proposed model in the CARLA simulator with extensive experiments which show remarkable interpretability, generalization, and robustness capability in unknown scenarios for navigation tasks.
关键词	Autonomous driving end-to-End driving imitation learning interpretability motion planning
DOI	10.1109/TIV.2022.3225340
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85144050330
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/11627
专题	北师香港浸会大学
通讯作者	Xuanyuan，Zhe
作者单位	1.BNU-HKBU United International College,Zhuhai,519087,China 2.Hong Kong Baptist University,Kowloon,999077,Hong Kong 3.Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex Systems,Institute of Automation,Beijing,100190,China 4.Waytous Inc. Qingdao,Qingdao,266109,China 5.University of Chinese Academy of Sciences,Beijing,100049,China 6.Malardalen University,Vasteras,72214,Sweden 7.Hubei University,School of Computer Science and Information Engineering,Wuhan,430062,China
第一作者单位	北师香港浸会大学
通讯作者单位	北师香港浸会大学
推荐引用方式 GB/T 7714	Teng，Siyu,Chen，Long,Ai，Yunfenget al. Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(1): 673-683.
APA	Teng，Siyu, Chen，Long, Ai，Yunfeng, Zhou，Yuanye, Xuanyuan，Zhe, & Hu，Xuemin. (2023). Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving. IEEE Transactions on Intelligent Vehicles, 8(1), 673-683.
MLA	Teng，Siyu,et al."Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving". IEEE Transactions on Intelligent Vehicles 8.1(2023): 673-683.