Long Short-Term Memory-Based Human-Driven Vehicle Longitudinal Trajectory Prediction in a Connected and Autonomous Vehicle Environment
Long Short-Term Memory-Based Human-Driven Vehicle Longitudinal Trajectory Prediction in a Connected and Autonomous Vehicle Environment
复制标题
联网和自主车辆环境中基于长短期记忆的人类驾驶车辆纵向轨迹预测
DOI：
10.1177/0361198121993471
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Xia Wu
中科院分区：
文献类型：
--
作者：
Lei Lin;Siyuan Gong;Srinivas Peeta;Xia Wu
互联和自动驾驶汽车（CAV）的出现将改变驾驶行为和出行环境，并为更安全，更顺畅和更智能的道路交通提供机会。在从目前的人类驾驶车辆（HDV）过渡到全CAV交通环境期间，道路交通将由HDV和CAV的“混合”交通流组成。配备多个传感器和车对车通信，CAV可以跟踪周围的HDV，并接收通信范围内其他CAV的轨迹数据。这些轨迹数据可以与深度学习方法的最新进展一起利用，以潜在地预测目标HDV的轨迹。基于这些预测，CAV可以做出反应，以规避或减轻交通流量波动和事故。本研究开发了基于注意力的长短期记忆（LSTM）模型，用于混合流环境中HDV纵向轨迹预测。该模型和其他一些LSTM变体在下一代模拟US 101数据集上进行了测试，具有不同的CAV市场渗透率（MPR）。结果表明，即使MPR低至0.2，利用周围CAV的历史轨迹的LSTM模型也比忽略信息的模型表现得更好。基于注意力的LSTM模型可以提供更准确的多步纵向轨迹预测。此外，网格级的平均注意力权重进行分析，并确定了对目标HDV的未来轨迹具有较高影响的CAV。
The advent of connected and autonomous vehicles (CAVs) will change driving behavior and travel environment, and provide opportunities for safer, smoother, and smarter road transportation. During the transition from the current human-driven vehicles (HDVs) to a fully CAV traffic environment, the road traffic will consist of a “mixed” traffic flow of HDVs and CAVs. Equipped with multiple sensors and vehicle-to-vehicle communications, a CAV can track surrounding HDVs and receive trajectory data of other CAVs in communication range. These trajectory data can be leveraged with recent advances in deep learning methods to potentially predict the trajectories of a target HDV. Based on these predictions, CAVs can react to circumvent or mitigate traffic flow oscillations and accidents. This study develops attention-based long short-term memory (LSTM) models for HDV longitudinal trajectory prediction in a mixed flow environment. The model and a few other LSTM variants are tested on the Next Generation Simulation US 101 dataset with different CAV market penetration rates (MPRs). Results illustrate that LSTM models that utilize historical trajectories from surrounding CAVs perform much better than those that ignore information even when the MPR is as low as 0.2. The attention-based LSTM models can provide more accurate multi-step longitudinal trajectory predictions. Further, grid-level average attention weight analysis is conducted and the CAVs with higher impact on the target HDV’s future trajectories are identified.
登录
查看更多内容
DOI：
10.1109/isai-nlp.2018.8692799
发表时间：
2018-07
期刊：
2018 International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)
影响因子：
--
作者：
Tao Li;Lei Lin;Minsoo Choi;Kaiming Fu;Siyuan Gong;Jian Wang
通讯作者：
Tao Li;Lei Lin;Minsoo Choi;Kaiming Fu;Siyuan Gong;Jian Wang
影响因子：
1.7
作者：
Saskia Ossen;S. Hoogendoorn
通讯作者：
Saskia Ossen;S. Hoogendoorn
DOI：
10.1007/978-3-030-61085-2_10
发表时间：
2021-01
期刊：
Narrative Inquiry into Reciprocal Learning Between Canada-China Sister Schools
影响因子：
--
作者：
Bu Yuhua
通讯作者：
Bu Yuhua
影响因子：
1.9
作者：
F. Wilcoxon
通讯作者：
F. Wilcoxon
影响因子：
2.6
作者：
Pendleton, Scott Drew;Andersen, Hans;Ang, Marcelo H., Jr.
通讯作者：
Ang, Marcelo H., Jr.