# Figure

Figure develops humanoid robots and publishes its own tests of how they perform physical tasks.

Type: organization. Context selected by Escape Meridian; inclusion is not endorsement.

[Collection](/entities/figure)
[Original website](https://www.figure.ai/news)

## Sources

- [Figure](https://www.figure.ai/news): Follow robots from controlled demonstrations into useful work, checking the tasks, failure rates and environments behind each result.

## Perspectives


## Terminal notes

- [A robot carries three learned tasks into unfamiliar homes](/notes/figure-unseen-homes-2026.md): Figure reports testing tidying, towel folding and bed making across 30 unseen homes. In its comparison, broad human-experience pretraining raised full-task success from 9% to 56%. That points toward less setup in each new workplace, while leaving substantial room for failure.

## Parallels


## Context references

- [https://www.figure.ai/news](https://www.figure.ai/news)
- [https://www.figure.ai/news/helix-2-5-zero-shot-30-home-generalization](https://www.figure.ai/news/helix-2-5-zero-shot-30-home-generalization)

Latest published distillations: [Publications API](/api/pipeline/publications?entity=figure)