Benchmarking Behavior Prediction Models in Gap Acceptance Scenarios

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)
45 Downloads (Pure)


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.

Original languageEnglish
Pages (from-to)2580-2591
JournalIEEE Transactions on Intelligent Vehicles
Issue number3
Publication statusPublished - 2023

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • Accidents
  • Autonomous vehicles
  • autonomous vehicles
  • behavior prediction
  • Behavioral sciences
  • benchmark
  • gap acceptance
  • Measurement
  • Predictive models
  • Safety
  • Trajectory


Dive into the research topics of 'Benchmarking Behavior Prediction Models in Gap Acceptance Scenarios'. Together they form a unique fingerprint.

Cite this