# Trajectory Prediction (6 timesteps) on NuScenes Top 1% hard samples

Source: [Trajectory Prediction (6 timesteps) on NuScenes Top 1% hard samples](<https://www.sota2.com/research/sota/trajectory-prediction-6-timesteps-on-nuscenes-top-1-percent-hard-samples>)

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

Data updated: 2026-02-26T06:11:04.766Z

Evaluation of trajectory prediction models specifically on the top 1% hardest samples subset of the NuScenes dataset, focusing on predictions over a 6-timestep horizon, measured using Minimum Average Displacement Error (minADE) and Minimum Final Displacement Error (minFDE).

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 (6 timesteps) |
| Dataset (including any stated split) | NuScenes Top 1% hard samples |
| Metric | minADE |
| 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](<https://www.sota2.com/research/sota/trajectory-prediction-6-timesteps-on-nuscenes-top-1-percent-hard-samples.md?metric=minADE>): Lower is better; unit: SCALAR.

- [minFDE](<https://www.sota2.com/research/sota/trajectory-prediction-6-timesteps-on-nuscenes-top-1-percent-hard-samples.md?metric=minFDE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | minADE | Result date | Report paper |
| --- | --- | --- | --- |
| Trajectron++ w/o RS + FEND | 1.24 | Not recorded | 68fa6ee31e209131cea42a4d |
| Trajectron++ + contrastive | 1.45 | Not recorded | 68fa6ee31e209131cea42a4d |
| Trajectron++ | 1.85 | Not recorded | 68fa6ee31e209131cea42a4d |

### Trajectron++ w/o RS + FEND

minADE: 1.24. Result ID: 699067c23a6c31484900505e.

[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: {"mode":"w/o RS"}. This record does not assert independent reproduction.

### Trajectron++ + contrastive

minADE: 1.45. Result ID: 699067c23a6c31484900505d.

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

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

Recorded evaluation configuration: {"mode":"contrastive"}. This record does not assert independent reproduction.

### Trajectron++

minADE: 1.85. Result ID: 699067c23a6c31484900505c.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa690e1e209131cea1fd3a.md>)

[Implementation](<https://github.com/StanfordASL/Trajectron-plus-plus>)

Recorded evaluation configuration: {"baseline":"standard"}. This record does not assert independent reproduction.

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