# Trajectory Planning on HUGSIM nuScenes (hard)

Source: [Trajectory Planning on HUGSIM nuScenes (hard)](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard>)

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

Data updated: 2026-04-07T07:15:45.541Z

Evaluation of trajectory planning performance on the 'hard' subset of the HUGSIM nuScenes dataset, assessed using HDScore components including NC, DAC, TTC, COM, Rc, and Overall HDScore.

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 Planning |
| Dataset (including any stated split) | HUGSIM nuScenes (hard) |
| Metric | NC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [NC](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=NC>): Higher is better; unit: SCALAR.

- [DAC](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=DAC>): Higher is better; unit: SCALAR.

- [TTC](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=TTC>): Higher is better; unit: SCALAR.

- [COM](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=COM>): Higher is better; unit: SCALAR.

- [Rc](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=Rc>): Higher is better; unit: SCALAR.

- [Overall HDScore](<https://www.sota2.com/research/sota/trajectory-planning-on-hugsim-nuscenes-hard.md?metric=Overall%20HDScore>): Higher is better; unit: SCALAR.

## Recorded results

| Method | NC | Result date | Report paper |
| --- | --- | --- | --- |
| Alpamayo | 0.968 | Not recorded | 68fa78c71e209131cea7a772 |
| OmniDrive | 0.757 | Not recorded | 68fa78c71e209131cea7a772 |
| UniAD | 0.716 | Not recorded | 68fa78c71e209131cea7a772 |
| VAD-Base | 0.631 | Not recorded | 68fa78c71e209131cea7a772 |
| VERDI | 0.623 | Not recorded | 68fa78c71e209131cea7a772 |
| OpenEMMA | 0.312 | Not recorded | 68fa78c71e209131cea7a772 |

### Alpamayo

NC: 0.968. Result ID: 69d4ae8e47f34ce924bc0612.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988743ef7ccd74e5e5a09.md>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"Yes","Number of Parameters (M)":"11079","Latency (ms)":"5246"}. This record does not assert independent reproduction.

### OmniDrive

NC: 0.757. Result ID: 69d4ae8e47f34ce924bc0614.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78031e209131cea76545.md>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"Yes","Number of Parameters (M)":"6849","Latency (ms)":"554"}. This record does not assert independent reproduction.

### UniAD

NC: 0.716. Result ID: 69d4ae8e47f34ce924bc0615.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c46.md>)

[Implementation](<https://github.com/OpenDriveLab/UniAD>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"No","Number of Parameters (M)":"132","Latency (ms)":"724"}. This record does not assert independent reproduction.

### VAD-Base

NC: 0.631. Result ID: 69d4ae8e47f34ce924bc0616.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70671e209131cea4af09.md>)

[Implementation](<https://github.com/hustvl/VAD>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"No","Number of Parameters (M)":"58","Latency (ms)":"359"}. This record does not assert independent reproduction.

### VERDI

NC: 0.623. Result ID: 69d4ae8e47f34ce924bc0617.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"No","Number of Parameters (M)":"58","Latency (ms)":"359"}. This record does not assert independent reproduction.

### OpenEMMA

NC: 0.312. Result ID: 69d4ae8e47f34ce924bc0613.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a772.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77071e209131cea709b4.md>)

Recorded evaluation configuration: {"Requires VLM @ Inference":"Yes","Number of Parameters (M)":"7000","Latency (ms)":"573"}. This record does not assert independent reproduction.

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