期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 22, 期 5, 页码 2669-2678出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2020.2973751
关键词
Vehicles; Task analysis; Hidden Markov models; Predictive models; Brain modeling; Cognition; Data models; Bi-LSTM; CRF; ADAS; recurrent neural networks; visual inertia; behavior prediction
资金
- National Key Research and Development Plan [2016YFB0100901]
- Beijing Municipal Science and Technology Project [Z191100007419001]
- National Natural Science Foundation of China [61773231]
- Cross-Disciplinary Research Innovation Fund of Graduate School at Shenzhen, Tsinghua University [JC2015002]
This paper introduces driving behavior modeling in a combination of cognitive and data-driven perspectives, proposes the Predictive-Bi-LSTM-CRF algorithm, and defines a new evaluation metric. Experimental results demonstrate the excellent performance of the algorithm in the prediction task.
Driving behavior plays a key role in the interaction between vehicle and driver in transportation systems. Some applications about driving behavior in Advanced Driver Assistance Systems (ADAS) improve driving safety significantly. This paper introduces the driving context and models driving behavior in a combination of cognitive perspective and data-driven perspective. First, we use a cognitive fusion method by adding a delay time module to fuse the environmental information and inside information. To better capture the driving context relationship between outside and inside features, we transfer the behavior prediction task to the sequence labeling task by introducing the visual inertia hypothesis. We propose the Predictive-Bi-LSTM-CRF algorithm which used the Bidirectional Long-Short Term Memory Networks (Bi-LSTM) and Conditional Random Field (CRF) as the loss layer to model the driving behavior. Besides, we define a new comprehensive evaluation metric for the prediction task considering F1-score and the prediction time before maneuver together. Our experiment results achieve the state of art performance on the Brain4Cars dataset and demonstrate the applicability of our theory.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据