Abstract
In recent years, a surging development of vehicles and continuous enhancement of transportation infrastructures have been witnessed worldwide, leading to a remarkable growing of traffic flow data. The traffic data is highly valuable in today’s society, accurate modelling of traffic flow for the concerned areas can significantly benefit the government agencies, related commercial departments and individuals. Specifically, road users are allowed to make better traveling decisions, avoid traffic congestion, reduce carbon emissions and improve traffic operation efficiency. In order to estimate the possible traffic flow scenarios within a specific area for multiple horizons, we propose a scenario generation model based on sequential generative adversarial networks (LSTM-GAN) where the long short term memory (LSTM) network is incorporated to capture the temporal dynamics involved in traffic flows. Through game training, the spatiotemporal scenarios of traffic flow in line with the characteristics of observed road network traffic flow can be well generated. These traffic scenarios can be applied in the design and planning of road traffic system, as well as in the virtual training cases of intelligent driving.
Highlights
The merits of the proposed model can be summarized as follows: i), Most of conventional scenario generation models require extensive work on parameter and condition setting, whereas the whole training process of long short term memory (LSTM)-generative adversarial networks (GAN) is completely data-driven, only historic samples are needed; ii), The generated scenarios in most of the existing works only consider one time slot or location, instead, the scenario data generated by the proposed LSTM-GAN can simultaneously cover consecutive time slots and multiple locations; iii), SGAN can learn the temporal dynamics, and takes into account the spatial characteristics; iv), LSTM-GAN has strong generalization capability to deal with different data
A novel data-driven model based on LSTM-GAN is proposed to produce the realistic traffic scenarios for multiple horizons and locations, which are highly beneficial to traffic infrastructure design and road planning
The LSTM-GAN leverages the merits of both LSTM and invert mapping networks
Summary
The data and information required by the TRANSYT system traffic model are: road network geometric characteristic, traffic volume data, economic indicators, etc This simulation software is limited by its high computational burden, which is more evident when the urban network is large. The merits of the proposed model can be summarized as follows: i), Most of conventional scenario generation models require extensive work on parameter and condition setting, whereas the whole training process of LSTM-GAN is completely data-driven, only historic samples are needed; ii), The generated scenarios in most of the existing works only consider one time slot or location, instead, the scenario data generated by the proposed LSTM-GAN can simultaneously cover consecutive time slots and multiple locations; iii), SGAN can learn the temporal dynamics, and takes into account the spatial characteristics; iv), LSTM-GAN has strong generalization capability to deal with different data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
