# Trajectory Prediction on nuScenes (test) using Percentile minADE/minFDE

Source: [Trajectory Prediction on nuScenes (test) using Percentile minADE/minFDE](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:11:05.567Z

Evaluation of trajectory prediction models on the test split of the nuScenes dataset, assessed using percentile-based Minimum Average Displacement Error (minADE) and Minimum Final Displacement Error (minFDE) across various confidence levels (1% to 5%, rest, and all).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Trajectory Prediction |
| Dataset (including any stated split) | nuScenes (test) |
| Metric | minADE (Top 1%) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [minADE (Top 1%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Top%201%25)>): Lower is better; unit: SCALAR.

- [minFDE (Top 1%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Top%201%25)>): Lower is better; unit: SCALAR.

- [minADE (Top 2%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Top%202%25)>): Lower is better; unit: SCALAR.

- [minFDE (Top 2%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Top%202%25)>): Lower is better; unit: SCALAR.

- [minADE (Top 3%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Top%203%25)>): Lower is better; unit: SCALAR.

- [minFDE (Top 3%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Top%203%25)>): Lower is better; unit: SCALAR.

- [minADE (Top 4%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Top%204%25)>): Lower is better; unit: SCALAR.

- [minFDE (Top 4%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Top%204%25)>): Lower is better; unit: SCALAR.

- [minADE (Top 5%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Top%205%25)>): Lower is better; unit: SCALAR.

- [minFDE (Top 5%)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Top%205%25)>): Lower is better; unit: SCALAR.

- [minADE (Rest)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(Rest)>): Lower is better; unit: SCALAR.

- [minFDE (Rest)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(Rest)>): Lower is better; unit: SCALAR.

- [minADE (All)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minADE%20(All)>): Lower is better; unit: SCALAR.

- [minFDE (All)](<https://www.sota2.com/research/sota/trajectory-prediction-on-nuscenes-test-using-percentile-minade-minfde.md?metric=minFDE%20(All)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | minADE (Top 1%) | Result date | Report paper |
| --- | --- | --- | --- |
| Traj++ EWTA w/o resampling+FEND | 1.21 | Not recorded | 68fa6ee31e209131cea42a4d |
| Traj++ EWTA+contrastive | 1.28 | Not recorded | 68fa6ee31e209131cea42a4d |
| Traj++ EWTA | 1.33 | Not recorded | 68fa6ee31e209131cea42a4d |

### Traj++ EWTA w/o resampling+FEND

minADE (Top 1%): 1.21. Result ID: 699067c23a6c314849005029.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42a4d.md>)

[Implementation](<https://github.com/ynw2021/FEND>)

Recorded evaluation configuration: {"Evaluation Protocol":"Best-of-20"}. This record does not assert independent reproduction.

### Traj++ EWTA+contrastive

minADE (Top 1%): 1.28. Result ID: 699067c23a6c314849005028.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b961e209131cea2f128.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Best-of-20"}. This record does not assert independent reproduction.

### Traj++ EWTA

minADE (Top 1%): 1.33. Result ID: 699067c23a6c314849005027.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b961e209131cea2f128.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Best-of-20"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.