ADE And FDE¶
Formula¶
trajectory_ade = mean(distance(predicted_i, ground_truth_i))
trajectory_fde = distance(predicted_last, ground_truth_last)
Hand-Computable Example¶
Prediction: (1, 0), (2, 2).
Ground truth: (1, 0), (2, 0).
Expected output: trajectory_ade = 1.0, trajectory_fde = 2.0.
Calculation: distances are 0 and 2, so ADE is (0 + 2) / 2 = 1.
Edge Cases¶
- Missing prediction or ground truth trajectory returns
0.0. - Points are paired by index.
Limitations¶
ADE/FDE are geometric errors only. They do not encode traffic rules, feasibility, comfort, or downstream control safety.
Test References¶
tests/golden/test_openloop_metrics_golden.pytests/test_openloop_metrics.py