# Quadruped Locomotion on Foam real-world (evaluation)

Source: [Quadruped Locomotion on Foam real-world (evaluation)](<https://www.sota2.com/research/sota/quadruped-locomotion-on-foam-real-world-evaluation>)

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

Data updated: 2026-03-18T06:51:22.040Z

Evaluation of quadruped locomotion performance within the Foam real-world environment, measured by forward progression and success rate.

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 | Quadruped Locomotion |
| Dataset (including any stated split) | Foam real-world (evaluation) |
| Metric | Forward Progression Distance |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Forward Progression Distance](<https://www.sota2.com/research/sota/quadruped-locomotion-on-foam-real-world-evaluation.md?metric=Forward%20Progression%20Distance>): Higher is better; unit: SCALAR.

- [Success Rate](<https://www.sota2.com/research/sota/quadruped-locomotion-on-foam-real-world-evaluation.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Forward Progression Distance | Result date | Report paper |
| --- | --- | --- | --- |
| SimDist | 3 | Not recorded | 69ba31710636e5bf4afc065c |
| SimDist | 3 | Not recorded | 69ba31710636e5bf4afc065c |
| SimDist | 3 | Not recorded | 69ba31710636e5bf4afc065c |
| Pretrained model | 2.98 | Not recorded | 69ba31710636e5bf4afc065c |
| IQL | 2.73 | Not recorded | 69ba31710636e5bf4afc065c |
| Single-step BC policy | 2.45 | Not recorded | 69ba31710636e5bf4afc065c |
| Pretrained model | 2.39 | Not recorded | 69ba31710636e5bf4afc065c |
| IQL | 2.25 | Not recorded | 69ba31710636e5bf4afc065c |
| Single-step BC policy | 2.07 | Not recorded | 69ba31710636e5bf4afc065c |
| Pretrained model | 1.7 | Not recorded | 69ba31710636e5bf4afc065c |
| Single-step BC policy | 1.54 | Not recorded | 69ba31710636e5bf4afc065c |
| IQL | 0.92 | Not recorded | 69ba31710636e5bf4afc065c |

### SimDist

Forward Progression Distance: 3. Result ID: 69ba49ce47f34ce924a383df.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.2 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

### SimDist

Forward Progression Distance: 3. Result ID: 69ba49ce47f34ce924a383e3.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.7 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

### SimDist

Forward Progression Distance: 3. Result ID: 69ba49ce47f34ce924a383e7.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"1.2 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

### Pretrained model

Forward Progression Distance: 2.98. Result ID: 69ba49ce47f34ce924a383dd.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.2 m s⁻¹","Evaluation Protocol":"Zero-shot deployment"}. This record does not assert independent reproduction.

### IQL

Forward Progression Distance: 2.73. Result ID: 69ba49ce47f34ce924a383e8.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

Recorded evaluation configuration: {"Speed":"1.2 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

### Single-step BC policy

Forward Progression Distance: 2.45. Result ID: 69ba49ce47f34ce924a383e6.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"1.2 m s⁻¹","Evaluation Protocol":"Pre-finetuning policy"}. This record does not assert independent reproduction.

### Pretrained model

Forward Progression Distance: 2.39. Result ID: 69ba49ce47f34ce924a383e1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.7 m s⁻¹","Evaluation Protocol":"Zero-shot deployment"}. This record does not assert independent reproduction.

### IQL

Forward Progression Distance: 2.25. Result ID: 69ba49ce47f34ce924a383e4.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

Recorded evaluation configuration: {"Speed":"0.7 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

### Single-step BC policy

Forward Progression Distance: 2.07. Result ID: 69ba49ce47f34ce924a383de.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.2 m s⁻¹","Evaluation Protocol":"Pre-finetuning policy"}. This record does not assert independent reproduction.

### Pretrained model

Forward Progression Distance: 1.7. Result ID: 69ba49ce47f34ce924a383e5.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"1.2 m s⁻¹","Evaluation Protocol":"Zero-shot deployment"}. This record does not assert independent reproduction.

### Single-step BC policy

Forward Progression Distance: 1.54. Result ID: 69ba49ce47f34ce924a383e2.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

Recorded evaluation configuration: {"Speed":"0.7 m s⁻¹","Evaluation Protocol":"Pre-finetuning policy"}. This record does not assert independent reproduction.

### IQL

Forward Progression Distance: 0.92. Result ID: 69ba49ce47f34ce924a383e0.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31710636e5bf4afc065c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

Recorded evaluation configuration: {"Speed":"0.2 m s⁻¹","Evaluation Protocol":"Real-world finetuning (32.1 min)"}. This record does not assert independent reproduction.

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