Saved in:
Bibliographic Details
Main Authors: He, Zhanpeng, Cao, Yifeng, Ciocarlie, Matei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.01876
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908584637366272
author He, Zhanpeng
Cao, Yifeng
Ciocarlie, Matei
author_facet He, Zhanpeng
Cao, Yifeng
Ciocarlie, Matei
contents Human-in-the-loop (HitL) robot deployment has gained significant attention in both academia and industry as a semi-autonomous paradigm that enables human operators to intervene and adjust robot behaviors at deployment time, improving success rates. However, continuous human monitoring and intervention can be highly labor-intensive and impractical when deploying a large number of robots. To address this limitation, we propose a method that allows diffusion policies to actively seek human assistance only when necessary, reducing reliance on constant human oversight. To achieve this, we leverage the generative process of diffusion policies to compute an uncertainty-based metric based on which the autonomous agent can decide to request operator assistance at deployment time, without requiring any operator interaction during training. Additionally, we show that the same method can be used for efficient data collection for fine-tuning diffusion policies in order to improve their autonomous performance. Experimental results from simulated and real-world environments demonstrate that our approach enhances policy performance during deployment for a variety of scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Models
He, Zhanpeng
Cao, Yifeng
Ciocarlie, Matei
Machine Learning
Robotics
Human-in-the-loop (HitL) robot deployment has gained significant attention in both academia and industry as a semi-autonomous paradigm that enables human operators to intervene and adjust robot behaviors at deployment time, improving success rates. However, continuous human monitoring and intervention can be highly labor-intensive and impractical when deploying a large number of robots. To address this limitation, we propose a method that allows diffusion policies to actively seek human assistance only when necessary, reducing reliance on constant human oversight. To achieve this, we leverage the generative process of diffusion policies to compute an uncertainty-based metric based on which the autonomous agent can decide to request operator assistance at deployment time, without requiring any operator interaction during training. Additionally, we show that the same method can be used for efficient data collection for fine-tuning diffusion policies in order to improve their autonomous performance. Experimental results from simulated and real-world environments demonstrate that our approach enhances policy performance during deployment for a variety of scenarios.
title Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Models
topic Machine Learning
Robotics
url https://arxiv.org/abs/2503.01876