Trajectory Prediction
Trajectory Prediction is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.
Source: Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs
Papers
Showing 1–10 of 1004 papers
All datasetsnuScenesStanford DroneETH/UCYETHJAADPIEActEVINTERACTION Dataset - ValidationPAIDTrajNetApolloScapeHEV-I
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Sophie | ADE-8/12 | 0.54 | — | Unverified |
| 2 | CGNS | ADE-8/12 | 0.49 | — | Unverified |
| 3 | Social-STGCNN | ADE-8/12 | 0.49 | — | Unverified |
| 4 | Social BiGAT | ADE-8/12 | 0.48 | — | Unverified |
| 5 | Next | ADE-8/12 | 0.46 | — | Unverified |
| 6 | TPNSTA | ADE-8/12 | 0.37 | — | Unverified |
| 7 | Social-Implicit | ADE-8/12 | 0.33 | — | Unverified |
| 8 | MANTRA | ADE-8/12 | 0.32 | — | Unverified |
| 9 | Transformer TF | ADE-8/12 | 0.31 | — | Unverified |
| 10 | PECNet | ADE-8/12 | 0.29 | — | Unverified |