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 | ExpertTraj | Avg AMD/AMV 8/12 | 19.2 | — | Unverified |
| 2 | Social-GAN | Avg AMD/AMV 8/12 | 1.42 | — | Unverified |
| 3 | Social-STGCNN | Avg AMD/AMV 8/12 | 1.26 | — | Unverified |
| 4 | Trajectron++ | Avg AMD/AMV 8/12 | 1.01 | — | Unverified |
| 5 | Social-Implicit | Avg AMD/AMV 8/12 | 0.9 | — | Unverified |