Learning to simulate vehicle trajectories from demonstrations

Guanjie Zheng, Hanyang Liu, Kai Xu, Zhenhui Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations


Traffic simulations can help to explore novel and efficient transportation solutions that overcome traffic problems such as traffic jams and road planning. Traditional traffic simulators usually leverage a car-following model to simulate the vehicle's behavior in the real-world traffic environment. However, these calibrated simplified physical models often fail to accurately predict the pattern of vehicle's movement in complicated real-world traffic environment. Considering the complexity and non-linearity of the real-world traffic, this paper unprecedentedly treat the problem of traffic simulation as a learning problem, and proposes learning to simulate (L2S) vehicle trajectory. We use the generative adversarial imitation learning framework to estimate the policy that provides sequential decisions for the vehicle given real-world demonstrations. The experiment on real-world traffic data shows the superior performance in simulating vehicle trajectories of our method compared to traditional traffic simulation approaches.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020
PublisherIEEE Computer Society
Number of pages4
ISBN (Electronic)9781728129037
StatePublished - Apr 2020
Event36th IEEE International Conference on Data Engineering, ICDE 2020 - Dallas, United States
Duration: Apr 20 2020Apr 24 2020

Publication series

NameProceedings - International Conference on Data Engineering
ISSN (Print)1084-4627


Conference36th IEEE International Conference on Data Engineering, ICDE 2020
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Information Systems


Dive into the research topics of 'Learning to simulate vehicle trajectories from demonstrations'. Together they form a unique fingerprint.

Cite this