Shuofeng Wang

Shuofeng Wang

Auto-generated profile, based on publicly available information

Shuofeng Wang

Department of Automation, Tsinghua University, Beijing 100084, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2022 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
SWShuofeng Wang
Shuofeng Wang
ZLZhiheng Li
Zhiheng Li
NXNa Xie
Na Xie

31 August 2020 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
SDShengzhe Dai
Shengzhe Dai
Zhiheng LiZhiheng Li
Zhiheng Li
LLLi Li
Li Li
NZNanning Zheng
Nanning Zheng
SWShuofeng Wang
Shuofeng Wang
Accurate trajectory prediction of surrounding vehicles is important for automated vehicles. To solve several existing problems of maneuver-based trajectory prediction, we propose four targeted solutions and establish a trajectory prediction model that integrates semi-supervised And-or Graph (AOG) and Spatio-temporal LSTM (ST-LSTM). To reduce the dependence on the well-labeled dataset, we introduce the concept of sub-maneuvers to improve the classifications of vehicle movements based on the given rough maneuver labels. AOG is used as the backbone of the probabilistic motion inference considering sub-maneuvers. We only define the basic units and inference logics of AOG and design a semi-supervised approach to directly learn the sub-maneuvers and the inference model structure from the training data, without manually specifying the structure (layers and nodes) of the inference model. This approach helps to avoid excessive artificial design or biases. The learned hierarchical motion inference model improves the interpretability of the overall trajectory prediction process. To utilize vehicle interaction information and further yield more accurate prediction, we adopt two different methods to consider vehicle interaction in the two sub-models (maneuver recognition and trajectory prediction). The experiment on NGSIM I-80 dataset shows that the maneuver-based model proposed in this paper (AOG-ST and refined AOG-ST-TB) performs more accurate trajectory prediction results. Although the AOG-ST seems clumsy and slow, we show that it is a flexible and quick model for trajectory prediction for various driving scenarios through the discussion and experiment.

1 October 2015
Verified
Conference Paper
Closed access
YWYanwei Wang
Yanwei Wang
LLLi Li
Li Li
JYJuntang Yu
Juntang Yu
Zhiheng LiZhiheng Li
Zhiheng Li
SWShuofeng Wang
Shuofeng Wang
Ruimin KeRuimin Ke
Ruimin Ke
Identifying the urban transportation corridor is very crucial in transportation planning, since planning with insufficient data verification often leads to wrong estimation of actual demand. In the era of big data, the pervasive penetration of mobile phones enables us to collect large-scale trajectory data of urban residents every day. These big data bring new opportunity to the data-driven and user-oriented transportation planning. Inspired by eigen-line concepts, this paper uses mobile phone users' record to identify transportation corridors in Shanghai. First, the transportation eigen-lines are identified by OD cluster method based on influence between OD links. Then, the obtained eigen-lines are testified by comparing with the real road network and population flow map to testify. Finally, the transportation corridors are drawn according to the determined eigen-lines and priori knowledge. The identified corridors reveal the spatial travel patterns of urban residents. These results help us understand the city transportation structure and travel demand features better.