Trajectory Forecasting on Univ UCY scene (test)
0.2ADETrajectron++
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Trajectron++mode=probabilistic, output_type=Full, best_of_n_samples=202020.01 | 0.2 | 0.44 | |
| Trajectron++mode=probabilistic, output_type=Full, best_of_n_samples=20, integration_via_dynamics=true2020.01 | 0.22 | 0.43 | |
| S-ATTNmode=deterministic2020.01 | 0.33 | 3.92 | |
| Trajectron++mode=deterministic, output_type=Most Likely (ML), integration_via_dynamics=true2020.01 | 0.41 | 1.07 | |
| Trajectron++mode=deterministic, output_type=Most Likely (ML)2020.01 | 0.44 | 1.17 | |
| MATFmode=probabilistic, best_of_n_samples=202020.01 | 0.44 | 0.91 | |
| SoPhiemode=probabilistic, best_of_n_samples=202020.01 | 0.54 | 1.24 | |
| Trajectronmode=probabilistic, best_of_n_samples=202020.01 | 0.54 | 1.13 | |
| S-GANmode=probabilistic, best_of_n_samples=202020.01 | 0.6 | 1.26 | |
| LSTMmode=deterministic2020.01 | 0.61 | 1.31 | |
| S-LSTMmode=deterministic2020.01 | 0.67 | 1.4 | |
| Linearmode=deterministic2020.01 | 0.82 | 1.59 |