# Learning latent dynamics on CS soft robot with one constant strain segment (test)

Source: [Learning latent dynamics on CS soft robot with one constant strain segment (test)](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-cs-soft-robot-with-one-constant-strain-segment-test>)

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

Data updated: 2026-02-26T05:59:58.564Z

Evaluation of model performance on learning the latent dynamics using the test split of the CS soft robot dataset (specifically the configuration with one constant strain segment), measured by RMSE, PSNR, and SSIM.

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 | Learning latent dynamics |
| Dataset (including any stated split) | CS soft robot with one constant strain segment (test) |
| Metric | RMSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [RMSE](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-cs-soft-robot-with-one-constant-strain-segment-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-cs-soft-robot-with-one-constant-strain-segment-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-cs-soft-robot-with-one-constant-strain-segment-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RMSE | Result date | Report paper |
| --- | --- | --- | --- |
| RNN | 0.1011 | Not recorded | 68fa75391e209131cea668c6 |
| CON-M | 0.1063 | Not recorded | 68fa75391e209131cea668c6 |
| GRU | 0.1125 | Not recorded | 68fa75391e209131cea668c6 |
| CFA-CON | 0.1462 | Not recorded | 68fa75391e209131cea668c6 |
| CON-S | 0.1993 | Not recorded | 68fa75391e209131cea668c6 |
| NODE | 0.2415 | Not recorded | 68fa75391e209131cea668c6 |
| MECH-NODE | 0.2494 | Not recorded | 68fa75391e209131cea668c6 |
| coRNN | 0.2537 | Not recorded | 68fa75391e209131cea668c6 |

### RNN

RMSE: 0.1011. Result ID: 699395293a6c31484917053a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"number of parameters":"696","latent dimension (nz)":"12"}. This record does not assert independent reproduction.

### CON-M

RMSE: 0.1063. Result ID: 699395293a6c314849170540.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"number of parameters":"8568","latent dimension (nz)":"12","size":"medium"}. This record does not assert independent reproduction.

### GRU

RMSE: 0.1125. Result ID: 699395293a6c31484917053b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617b1e209131ce9f462d.md>)

Recorded evaluation configuration: {"number of parameters":"2040","latent dimension (nz)":"12"}. This record does not assert independent reproduction.

### CFA-CON

RMSE: 0.1462. Result ID: 699395293a6c314849170541.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"number of parameters":"8568","latent dimension (nz)":"12"}. This record does not assert independent reproduction.

### CON-S

RMSE: 0.1993. Result ID: 699395293a6c31484917053f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"number of parameters":"1386","latent dimension (nz)":"12","size":"small"}. This record does not assert independent reproduction.

### NODE

RMSE: 0.2415. Result ID: 699395293a6c31484917053d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cb1e209131cea12502.md>)

[Implementation](<https://www.sota2.com/github.com/rtqichen/torchdiffeq>)

Recorded evaluation configuration: {"number of parameters":"4374","latent dimension (nz)":"12"}. This record does not assert independent reproduction.

### MECH-NODE

RMSE: 0.2494. Result ID: 699395293a6c31484917053e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"number of parameters":"4002","latent dimension (nz)":"12","prior knowledge":"mechanical structure"}. This record does not assert independent reproduction.

### coRNN

RMSE: 0.2537. Result ID: 699395293a6c31484917053c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea22495.md>)

Recorded evaluation configuration: {"number of parameters":"336","latent dimension (nz)":"12"}. This record does not assert independent reproduction.

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