Abstract
Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior, which could be improved by accurate and reliable prediction models enabling more efficient trajectory planning. However, the evaluation of such models is commonly over-simplistic, 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 language | English |
|---|---|
| Title of host publication | Proceedings of the 35th IEEE Intelligent Vehicles Symposium, IV 2024 |
| Publisher | IEEE |
| Pages | 3148 |
| Number of pages | 1 |
| ISBN (Electronic) | 9798350348811 |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 35th IEEE Intelligent Vehicles Symposium, IV 2024 - Jeju Island, Korea, Republic of Duration: 2 Jun 2024 → 5 Jun 2024 |
Publication series
| Name | IEEE Intelligent Vehicles Symposium, Proceedings |
|---|---|
| ISSN (Print) | 1931-0587 |
| ISSN (Electronic) | 2642-7214 |
Conference
| Conference | 35th IEEE Intelligent Vehicles Symposium, IV 2024 |
|---|---|
| Country/Territory | Korea, Republic of |
| City | Jeju Island |
| Period | 2/06/24 → 5/06/24 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise 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.