End‐to‐end learning for high‐precision lane keeping via multi‐state model. Issue 4 (20th November 2018)

• Record Type: Journal Article
• Authors: Yuan, Wei; Yang, Ming; Li, Hao; Wang, Chunxiang; Wang, Bing
• Is Part Of: CAAI transactions on intelligence technology. Volume 3:Issue 4(2018)
• Page Start: 185
• Page End: 190
• Publication Date: 2018-11-20
• Subjects: road vehicles -- finite state machines -- position control -- learning systems; driving states -- 3DCNN‐LSTM model -- lane keeping error -- multistate model‐based end‐to‐end method -- end‐to‐end learning -- high‐precision lane keeping -- future autonomous driving -- finite‐state machine -- multistate model‐based end‐to‐end lane keeping method; C1340E Self‐adjusting control systems -- C3120C Spatial variables control -- C3360B Road‐traffic system control -- C4220 Automata theory; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/trit.2018.1025
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract : High‐precision lane keeping is essential for the future autonomous driving. However, due to the imbalanced and inaccurate datasets collected by human drivers, current end‐to‐end driving models have poor lane keeping the effect. To improve the precision of lane keeping, this study presents a novel multi‐state model‐based end‐to‐end lane keeping method. First, three driving states will be defined: going straight, turning right and turning left. Second, the finite‐state machine (FSM) table as well as three kinds of training datasets will be generated based on the three driving states. Instead of collecting the dataset by human drivers, the accurate dataset will be collected by the high‐performance path following controller. Third, three sets of parameters based on 3DCNN‐LSTM model will be trained for going straight, turning left and turning right, which will be combined with FSM table to form a multi‐state model. This study evaluates the multi‐state model by testing it on five tracks and recording the lane keeping error. The result shows the multi‐state model‐based end‐to‐end method performs the higher precision of lane keeping than the traditional single end‐to‐end model.