MSE(0.5): 82MSE(1.0): 328MSE(1.5): 1049C_MSE(1.5): 996
Papers with Code · CC BY-SA 4.0
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.
<span class="description-source">Source: Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs </span>
논문
ADE: 0.005
ADE-8/12: 0.39
BLEU: 29.7DTW R@1: 19.7Accuracy: 28.9
RMSE: 5.63
MSE(0.5): 147MSE(1.0): 484MSE(1.5): 1374C_MSE(1.5): 1290
MSE(0.5): 93MSE(1.0): 378MSE(1.5): 1206C_MSE(1.5): 1105
ADE: 9.18FDE: 13.54
minADE (K=6): 0.69minFDE (K=6): 1.34MR (K=6): 0.18brier-minFDE (K=6): 1.90
ADE-8/12: 0.18FDE-8/12: 0.27
ADE-8/12: 0.17FDE-8/12: 0.24
MSE(0.5): 159MSE(1.0): 539MSE(1.5): 1535C_MSE(1.5): 1447
MSE(0.5): 110MSE(1.0): 399MSE(1.5): 1280C_MSE(1.5): 1183
ADE: 0.88FDE: 1.96
FDE: 5.992
FDE: 208ADE: 192STB: 11
Avg AMD/AMV 8/12: 1.42
Avg AMD/AMV 8/12: 0.90
Avg AMD/AMV 8/12: 1.26
ADE: 8.5881
Avg AMD/AMV 8/12: 1.01
ADE-8/12: 0.18FDE-8/12: 0.28
Avg AMD/AMV 8/12: 19.20