# I3L proposes iterative interactive imitation learning for whole-body mobile manipulation robots

> Original title: Long-horizon, whole-body robot policies still fail during deployment. How do we best close this last-mile gap? 🤖

- Source: X search: AI launch posts (introducing, just launched)
- Published: 2026-10-29T19:15:22.000Z
- Bad Influence: https://badinfluence.news/items/dy2ogti73mwlblrgk6bgulwsx
- Original: https://x.com/wensi_ai/status/2115885219815493909

## Summary

Researchers introduce I3L, an iterative interactive imitation learning method for whole-body mobile manipulation, aimed at closing the gap where long-horizon robot policies fail during deployment. The post links a project website and an arXiv paper, arXiv 2610.17748.

## Post

Long-horizon, whole-body robot policies still fail during deployment. How do we best close this last-mile gap? 🤖

🚨 Introducing I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation

Website: https://i-3l.github.io/
Paper: https://arxiv.org/abs/2610.17748

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2115885130690756608%2Fimg%2FnPDtBKHYxQT0ek3V.jpg&mode=thumb&exp=1793577600&sig=c17e4f1c2703462c)