Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios
This addresses the need for better evaluation methods to improve autonomous vehicle assertiveness in traffic interactions, though it is incremental as it focuses on benchmarking rather than new prediction models.
The paper tackles the problem of inefficient autonomous vehicle driving due to uncertainty in predicting human behavior by proposing a framework to evaluate prediction models in gap acceptance scenarios, finding that state-of-the-art models are unreliable in safety-critical situations.
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.