# Social Navigation Metric Evaluation on SocNav (test)

Source: [Social Navigation Metric Evaluation on SocNav (test)](<https://www.sota2.com/research/sota/social-navigation-metric-evaluation-on-socnav-test>)

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

Data updated: 2026-07-07T09:42:18.741Z

Evaluation of social navigation performance on the test split of the SocNav dataset, measured using Pearson and Spearman correlation coefficients.

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 | Social Navigation Metric Evaluation |
| Dataset (including any stated split) | SocNav (test) |
| Metric | Pearson Correlation (r) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Pearson Correlation (r)](<https://www.sota2.com/research/sota/social-navigation-metric-evaluation-on-socnav-test.md?metric=Pearson%20Correlation%20(r)>): Higher is better; unit: SCALAR.

- [Spearman Correlation (p)](<https://www.sota2.com/research/sota/social-navigation-metric-evaluation-on-socnav-test.md?metric=Spearman%20Correlation%20(p)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Pearson Correlation (r) | Result date | Report paper |
| --- | --- | --- | --- |
| ALT metric | 0.797 | Not recorded | 68fa7b101e209131cea8678b |
| success | 0.366 | Not recorded | 68fa7b101e209131cea8678b |
| min. time to collision | 0.121 | Not recorded | 68fa7b101e209131cea8678b |
| path efficiency ratio | 0.105 | Not recorded | 68fa7b101e209131cea8678b |
| cumulative heading changes | 0.049 | Not recorded | 68fa7b101e209131cea8678b |
| min. distance to humans | 0.009 | Not recorded | 68fa7b101e209131cea8678b |
| min. distance to objects | -0.006 | Not recorded | 68fa7b101e209131cea8678b |
| maximum panic | -0.128 | Not recorded | 68fa7b101e209131cea8678b |
| social space intrusions ratio | -0.184 | Not recorded | 68fa7b101e209131cea8678b |
| max. num. of near humans | -0.253 | Not recorded | 68fa7b101e209131cea8678b |
| social space intrusions ratio | -0.271 | Not recorded | 68fa7b101e209131cea8678b |
| max. num. of near humans | -0.303 | Not recorded | 68fa7b101e209131cea8678b |
| social space intrusions ratio | -0.316 | Not recorded | 68fa7b101e209131cea8678b |
| max. fear | -0.341 | Not recorded | 68fa7b101e209131cea8678b |
| collisions with humans | -0.385 | Not recorded | 68fa7b101e209131cea8678b |
| collisions with objects | -0.387 | Not recorded | 68fa7b101e209131cea8678b |
| max. num. of near humans | -0.415 | Not recorded | 68fa7b101e209131cea8678b |

### ALT metric

Pearson Correlation (r): 0.797. Result ID: 6a4cc9e360b88bb339c9caa3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### success

Pearson Correlation (r): 0.366. Result ID: 6a4cc9e360b88bb339c9ca93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### min. time to collision

Pearson Correlation (r): 0.121. Result ID: 6a4cc9e360b88bb339c9ca9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### path efficiency ratio

Pearson Correlation (r): 0.105. Result ID: 6a4cc9e360b88bb339c9caa1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### cumulative heading changes

Pearson Correlation (r): 0.049. Result ID: 6a4cc9e360b88bb339c9caa2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### min. distance to humans

Pearson Correlation (r): 0.009. Result ID: 6a4cc9e360b88bb339c9ca94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### min. distance to objects

Pearson Correlation (r): -0.006. Result ID: 6a4cc9e360b88bb339c9ca95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### maximum panic

Pearson Correlation (r): -0.128. Result ID: 6a4cc9e360b88bb339c9caa0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### social space intrusions ratio

Pearson Correlation (r): -0.184. Result ID: 6a4cc9e360b88bb339c9ca9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.8"}. This record does not assert independent reproduction.

### max. num. of near humans

Pearson Correlation (r): -0.253. Result ID: 6a4cc9e360b88bb339c9ca9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.8"}. This record does not assert independent reproduction.

### social space intrusions ratio

Pearson Correlation (r): -0.271. Result ID: 6a4cc9e360b88bb339c9ca99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.6"}. This record does not assert independent reproduction.

### max. num. of near humans

Pearson Correlation (r): -0.303. Result ID: 6a4cc9e360b88bb339c9ca9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.6"}. This record does not assert independent reproduction.

### social space intrusions ratio

Pearson Correlation (r): -0.316. Result ID: 6a4cc9e360b88bb339c9ca98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.4"}. This record does not assert independent reproduction.

### max. fear

Pearson Correlation (r): -0.341. Result ID: 6a4cc9e360b88bb339c9ca9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### collisions with humans

Pearson Correlation (r): -0.385. Result ID: 6a4cc9e360b88bb339c9ca96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### collisions with objects

Pearson Correlation (r): -0.387. Result ID: 6a4cc9e360b88bb339c9ca97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### max. num. of near humans

Pearson Correlation (r): -0.415. Result ID: 6a4cc9e360b88bb339c9ca9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b101e209131cea8678b.md>)

Recorded evaluation configuration: {"Distance Threshold":"0.4"}. This record does not assert independent reproduction.

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