Learning to Simulate on Sparse Trajectory Data

TL;DR

This paper introduces ImInGAIL, a novel framework that effectively learns driving behavior from sparse real-world traffic data by integrating data interpolation with imitation learning, improving simulation accuracy.

Contribution

The paper presents the first approach to address data sparsity in behavior learning for traffic simulation using an integrated interpolation and imitation learning framework.

Findings

Outperforms baseline methods on synthetic datasets

Achieves better realism in real-world traffic simulations

Effectively handles sparse trajectory data

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.