English

Learning to Simulate on Sparse Trajectory Data

Machine Learning 2021-03-24 v1 Artificial Intelligence

Abstract

Simulation of the real-world traffic can be used to help validate the transportation policies. A good simulator means the simulated traffic is similar to real-world traffic, which often requires dense traffic trajectories (i.e., with a high sampling rate) to cover dynamic situations in the real world. However, in most cases, the real-world trajectories are sparse, which makes simulation challenging. In this paper, we present a novel framework ImInGAIL to address the problem of learning to simulate the driving behavior from sparse real-world data. The proposed architecture incorporates data interpolation with the behavior learning process of imitation learning. To the best of our knowledge, we are the first to tackle the data sparsity issue for behavior learning problems. We investigate our framework on both synthetic and real-world trajectory datasets of driving vehicles, showing that our method outperforms various baselines and state-of-the-art methods.

Keywords

Cite

@article{arxiv.2103.11845,
  title  = {Learning to Simulate on Sparse Trajectory Data},
  author = {Hua Wei and Chacha Chen and Chang Liu and Guanjie Zheng and Zhenhui Li},
  journal= {arXiv preprint arXiv:2103.11845},
  year   = {2021}
}

Comments

Accepted by ECML-PKDD 2020, Best Applied Data Science Paper. 16 pages, 6 figures

R2 v1 2026-06-24T00:25:27.903Z