Learning to Simulate on Sparse Trajectory Data
This addresses the issue of sparse data for traffic simulation, which is crucial for validating transportation policies, but it is incremental as it builds on existing imitation learning methods.
The paper tackles the problem of simulating driving behavior from sparse real-world trajectory data, which is challenging due to low sampling rates, and presents ImInGAIL, a framework that integrates data interpolation with imitation learning, showing it outperforms baselines and state-of-the-art methods on synthetic and real-world datasets.
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.