# ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation

arXiv: https://arxiv.org/abs/2510.02298 · HTML: https://mlsanity.com/paper/2510.02298/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 2 Oct 2025.

## Placed in

- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Built on by (most cited first, 3 of 3)

- [UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning](https://mlsanity.com/paper/2606.12372/) (2026)
- [Accelerating Robotic Reinforcement Learning with Agent Guidance](https://mlsanity.com/paper/2602.11978/) (2026)
- [Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models](https://mlsanity.com/paper/2610.04054/) (2026)

## Abstract (arXiv)

Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Besides, human-collected demonstrations entail substantial labour and tend to encompass mixed-quality data and redundant information. As a workaround, human-in-the-loop systems gather domain-specific data for policy post-training, and exploit closed-loop policy feedback to offer informative guidance, but usually require full-time human surveillance during policy rollout. In this work, we devise ARMADA, a multi-robot deployment and adaptation system with human-in-the-loop shared control, featuring an autonomous online failure detection method named FLOAT. Thanks to FLOAT, ARMADA enables paralleled policy rollout and requests human intervention only when necessary, significantly reducing reliance on human supervision. Hence, ARMADA enables efficient acquisition of in-domain data, and leads to more scalable deployment and faster adaptation to new scenarios. We evaluate the performance of ARMADA on four real-world tasks. FLOAT achieves nearly 95% accuracy on average, surpassing prior state-of-the-art failure detection approaches by over 20%. Besides, ARMADA manifests more than 4× increase in success rate and greater than 2× reduction in human intervention rate over multiple rounds of policy rollout and post-training, compared to previous human-in-the-loop learning methods.