# Trajectory Prediction on Euro-PVI (test) Source: [Trajectory Prediction on Euro-PVI (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:52.921Z Evaluation of trajectory prediction models on the test split of the Euro-PVI dataset, typically assessed using Best of N (BoN) and Kernel Density Estimation Negative Log-Likelihood (KDE NLL) metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Trajectory Prediction | | Dataset (including any stated split) | Euro-PVI (test) | | Metric | BoN@20 (t+1s) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [BoN@20 (t+1s)](): Higher is better; unit: PERCENT. - [BoN@20 (t+2s)](): Higher is better; unit: PERCENT. - [BoN@20 (t+3s)](): Higher is better; unit: PERCENT. - [KDE NLL (t+1s)](): Lower is better; unit: SCALAR. - [KDE NLL (t+2s)](): Lower is better; unit: SCALAR. - [KDE NLL (t+3s)](): Lower is better; unit: SCALAR. ## Recorded results | Method | BoN@20 (t+1s) | Result date | Report paper | | --- | --- | --- | --- | | Social-GAN | 14 | Not recorded | 68fa6a381e209131cea26aeb | | Social-GAN | 14 | Not recorded | 68fa6a381e209131cea26aeb | | CVAE | 12 | Not recorded | 68fa6a381e209131cea26aeb | | Sophie | 11 | Not recorded | 68fa6a381e209131cea26aeb | | Sophie | 11 | Not recorded | 68fa6a381e209131cea26aeb | | beta-CVAE | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Trajectron++ | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Trajectron++ | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-β-cVAE | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-β-cVAE | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Trajectron++ | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-β-cVAE | 10 | Not recorded | 68fa6a381e209131cea26aeb | | Trajectron++ | 9 | Not recorded | 68fa6a381e209131cea26aeb | | Trajectron++ | 9 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-beta-cVAE | 9 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-beta-cVAE | 9 | Not recorded | 68fa6a381e209131cea26aeb | | Joint-beta-cVAE | 9 | Not recorded | 68fa6a381e209131cea26aeb | ### Social-GAN BoN@20 (t+1s): 14. Result ID: 698e1ec8ffc3901de09af071. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":false,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Social-GAN BoN@20 (t+1s): 14. Result ID: 698e1ec8ffc3901de09af072. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":true}. This record does not assert independent reproduction. ### CVAE BoN@20 (t+1s): 12. Result ID: 698e1ec8ffc3901de09af077. [Reporting paper]() Recorded evaluation configuration: {"P-P Interaction modeling":false,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Sophie BoN@20 (t+1s): 11. Result ID: 698e1ec8ffc3901de09af073. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Sophie BoN@20 (t+1s): 11. Result ID: 698e1ec8ffc3901de09af074. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":true}. This record does not assert independent reproduction. ### beta-CVAE BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af078. [Reporting paper]() Recorded evaluation configuration: {"P-P Interaction modeling":false,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Trajectron++ BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af086. [Reporting paper]() Recorded evaluation configuration: {"P-P (Pedestrian-Pedestrian) Interaction Modeling":true,"P-V (Pedestrian-Vehicle) Interaction Modeling":false}. This record does not assert independent reproduction. ### Trajectron++ BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af087. [Reporting paper]() Recorded evaluation configuration: {"P-P (Pedestrian-Pedestrian) Interaction Modeling":true,"P-V (Pedestrian-Vehicle) Interaction Modeling":true}. This record does not assert independent reproduction. ### Joint-β-cVAE BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af088. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P (Pedestrian-Pedestrian) Interaction Modeling":true,"P-V (Pedestrian-Vehicle) Interaction Modeling":false}. This record does not assert independent reproduction. ### Joint-β-cVAE BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af089. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P (Pedestrian-Pedestrian) Interaction Modeling":true,"P-V (Pedestrian-Vehicle) Interaction Modeling":true}. This record does not assert independent reproduction. ### Trajectron++ BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af08a. [Reporting paper]() Recorded evaluation configuration: {"Best of N":"20","Pre-trained on":"nuScenes"}. This record does not assert independent reproduction. ### Joint-β-cVAE BoN@20 (t+1s): 10. Result ID: 698e1ec8ffc3901de09af08b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Best of N":"20","Pre-trained on":"nuScenes"}. This record does not assert independent reproduction. ### Trajectron++ BoN@20 (t+1s): 9. Result ID: 698e1ec8ffc3901de09af075. [Reporting paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Trajectron++ BoN@20 (t+1s): 9. Result ID: 698e1ec8ffc3901de09af076. [Reporting paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":true}. This record does not assert independent reproduction. ### Joint-beta-cVAE BoN@20 (t+1s): 9. Result ID: 698e1ec8ffc3901de09af079. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":true}. This record does not assert independent reproduction. ### Joint-beta-cVAE BoN@20 (t+1s): 9. Result ID: 698e1ec8ffc3901de09af07a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":false}. This record does not assert independent reproduction. ### Joint-beta-cVAE BoN@20 (t+1s): 9. Result ID: 698e1ec8ffc3901de09af07b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"P-P Interaction modeling":true,"P-V Interaction modeling":false,"Input Modality (Camera, Lidar)":"Camera, Lidar"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.