English

Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios

Robotics 2023-02-21 v2 Machine Learning

Abstract

Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior in traffic interactions. Accurate and reliable prediction models enabling more efficient trajectory planning could make autonomous vehicles more assertive in such interactions. However, the evaluation of such models is commonly oversimplistic, ignoring the asymmetric importance of prediction errors and the heterogeneity of the datasets used for testing. We examine the potential of recasting interactions between vehicles as gap acceptance scenarios and evaluating models in this structured environment. To that end, we develop a framework aiming to facilitate the evaluation of any model, by any metric, and in any scenario. We then apply this framework to state-of-the-art prediction models, which all show themselves to be unreliable in the most safety-critical situations.

Keywords

Cite

@article{arxiv.2211.05455,
  title  = {Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios},
  author = {Julian Frederik Schumann and Jens Kober and Arkady Zgonnikov},
  journal= {arXiv preprint arXiv:2211.05455},
  year   = {2023}
}

Comments

11 pages, 5 figures, accepted by in IEEE Transactions on Intelligent Vehicles, 2023

R2 v1 2026-06-28T05:35:12.114Z