Details
| Original language | English |
|---|---|
| Title of host publication | Geospatial Technologies for All - Selected Papers of the 21st AGILE Conference on Geographic Information Science |
| Pages | 309-325 |
| Number of pages | 17 |
| Publication status | Published - 24 Dec 2018 |
| Event | 21st AGILE Conference on Geographic Information Science, 2018 - Lund, Sweden Duration: 12 Jun 2018 → 15 Jun 2018 |
Publication series
| Name | Lecture Notes in Geoinformation and Cartography |
|---|---|
| ISSN (Print) | 1863-2246 |
| ISSN (electronic) | 1863-2351 |
Abstract
Real–world behaviors of human road users in a non-regulated space (shared space) are complex. Firstly, there is no explicit regulation in such an area. Users self-organize to share the space. They are more likely to use as little energy as possible to reach their destinations in the shortest possible way, and try to avoid any potential collision. Secondly, different types of users (pedestrians, cyclists, and vehicles) behave differently. For example, pedestrians are more flexible to change their speed and trajectory, while cyclists and vehicles are more or less limited by their travel device—abrupt changes might lead to danger. While there are established models to describe the behavior of individual humans (e.g. Social Force model), due to the heterogeneity of transport modes and diversity of environments, hand-crafted models have difficulties in handling complicated interactions in mixed traffic. To this end, this paper proposes using a Long Short–Term Memory (LSTM) recurrent neural networks based deep learning approach to model user behaviors. It encodes user position coordinates, sight of view, and interactions between different types of neighboring users as spatio–temporal features to predict future trajectories with collision avoidance. The real–world data–driven method can be trained with pre-defined neural networks to circumvent complex manual design and calibration. The results show that ViewType-LSTM, which mimics how a human sees and reacts to different transport modes can well predict mixed traffic trajectories in a shared space at least in the next 3 s, and is also robust in complicated situations.
Keywords
- Long short–term memory, Mixed traffic, Shared space, Trajectory prediction
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
- Social Sciences(all)
- Geography, Planning and Development
- Earth and Planetary Sciences(all)
- Earth-Surface Processes
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Geospatial Technologies for All - Selected Papers of the 21st AGILE Conference on Geographic Information Science. 2018. p. 309-325 (Lecture Notes in Geoinformation and Cartography).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Mixed traffic trajectory prediction using LSTM–based models in shared space
AU - Cheng, Hao
AU - Sester, Monika
N1 - Funding Information: Acknowledgements The authors cordially thank the funding provided by DFG Training Group 1931 for SocialCars and the participants of the research project MODIS (Multi mODal Intersection Simulation) for providing the dataset of road user trajectories used in this work. Funding Information: The authors cordially thank the funding provided by DFG Training Group 1931 for SocialCars and the participants of the research project MODIS (Multi mODal Intersection Simulation) for providing the dataset of road user trajectories used in this work. Publisher Copyright: © Springer International Publishing AG, part of Springer Nature 2018. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/12/24
Y1 - 2018/12/24
N2 - Real–world behaviors of human road users in a non-regulated space (shared space) are complex. Firstly, there is no explicit regulation in such an area. Users self-organize to share the space. They are more likely to use as little energy as possible to reach their destinations in the shortest possible way, and try to avoid any potential collision. Secondly, different types of users (pedestrians, cyclists, and vehicles) behave differently. For example, pedestrians are more flexible to change their speed and trajectory, while cyclists and vehicles are more or less limited by their travel device—abrupt changes might lead to danger. While there are established models to describe the behavior of individual humans (e.g. Social Force model), due to the heterogeneity of transport modes and diversity of environments, hand-crafted models have difficulties in handling complicated interactions in mixed traffic. To this end, this paper proposes using a Long Short–Term Memory (LSTM) recurrent neural networks based deep learning approach to model user behaviors. It encodes user position coordinates, sight of view, and interactions between different types of neighboring users as spatio–temporal features to predict future trajectories with collision avoidance. The real–world data–driven method can be trained with pre-defined neural networks to circumvent complex manual design and calibration. The results show that ViewType-LSTM, which mimics how a human sees and reacts to different transport modes can well predict mixed traffic trajectories in a shared space at least in the next 3 s, and is also robust in complicated situations.
AB - Real–world behaviors of human road users in a non-regulated space (shared space) are complex. Firstly, there is no explicit regulation in such an area. Users self-organize to share the space. They are more likely to use as little energy as possible to reach their destinations in the shortest possible way, and try to avoid any potential collision. Secondly, different types of users (pedestrians, cyclists, and vehicles) behave differently. For example, pedestrians are more flexible to change their speed and trajectory, while cyclists and vehicles are more or less limited by their travel device—abrupt changes might lead to danger. While there are established models to describe the behavior of individual humans (e.g. Social Force model), due to the heterogeneity of transport modes and diversity of environments, hand-crafted models have difficulties in handling complicated interactions in mixed traffic. To this end, this paper proposes using a Long Short–Term Memory (LSTM) recurrent neural networks based deep learning approach to model user behaviors. It encodes user position coordinates, sight of view, and interactions between different types of neighboring users as spatio–temporal features to predict future trajectories with collision avoidance. The real–world data–driven method can be trained with pre-defined neural networks to circumvent complex manual design and calibration. The results show that ViewType-LSTM, which mimics how a human sees and reacts to different transport modes can well predict mixed traffic trajectories in a shared space at least in the next 3 s, and is also robust in complicated situations.
KW - Long short–term memory
KW - Mixed traffic
KW - Shared space
KW - Trajectory prediction
UR - http://www.scopus.com/inward/record.url?scp=85044822355&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-78208-9_16
DO - 10.1007/978-3-319-78208-9_16
M3 - Conference contribution
AN - SCOPUS:85044822355
SN - 9783319782072
T3 - Lecture Notes in Geoinformation and Cartography
SP - 309
EP - 325
BT - Geospatial Technologies for All - Selected Papers of the 21st AGILE Conference on Geographic Information Science
T2 - 21st AGILE Conference on Geographic Information Science, 2018
Y2 - 12 June 2018 through 15 June 2018
ER -