# CrowdMAPS lets crowds label multiple robot actions per state

> A web tool lets remote annotators add up to ten alternative actions for each robot state, boosting success rates by about 35% on real tasks.

Oossa · 2026-11-13 · https://oossa.com/en/crowdmaps-lets-crowds-label-multiple-robot-actions-per-state

Researchers introduced CrowdMAPS, a web‑based system that shows robot states to online workers through a 3‑D interface. Workers add valid alternative actions without touching the robot. The method adds a “width” dimension to robot data by increasing actions per state instead of collecting more trajectories. Tests on five real‑world manipulation tasks showed that expanding from one to ten actions per state lifted average success rates by 35.6 percentage points for keypose policies and 33.0 points for trajectory policies.

## The facts

- Up to ten alternative actions per visited state were collected.
- Success rates rose 35.6 % for keypose policies and 33.0 % for trajectory policies.

## Why it matters

Developers can train more reliable robots with fewer physical demonstrations, saving time and cost.

## Sources & references

1. [CrowdMAPS: Crowdsourcing Multiple Actions per State for Real-World Imitation Learning](https://arxiv.org/abs/2611.15078) – arXiv cs.RO, 2026-11-13

Last updated: 2026-11-13