Saved in:
Bibliographic Details
Main Authors: Haldar, Siddhant, Pinto, Lerrel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.20391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913711026864128
author Haldar, Siddhant
Pinto, Lerrel
author_facet Haldar, Siddhant
Pinto, Lerrel
contents Building robotic agents capable of operating across diverse environments and object types remains a significant challenge, often requiring extensive data collection. This is particularly restrictive in robotics, where each data point must be physically executed in the real world. Consequently, there is a critical need for alternative data sources for robotics and frameworks that enable learning from such data. In this work, we present Point Policy, a new method for learning robot policies exclusively from offline human demonstration videos and without any teleoperation data. Point Policy leverages state-of-the-art vision models and policy architectures to translate human hand poses into robot poses while capturing object states through semantically meaningful key points. This approach yields a morphology-agnostic representation that facilitates effective policy learning. Our experiments on 8 real-world tasks demonstrate an overall 75% absolute improvement over prior works when evaluated in identical settings as training. Further, Point Policy exhibits a 74% gain across tasks for novel object instances and is robust to significant background clutter. Videos of the robot are best viewed at https://point-policy.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20391
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation
Haldar, Siddhant
Pinto, Lerrel
Robotics
Building robotic agents capable of operating across diverse environments and object types remains a significant challenge, often requiring extensive data collection. This is particularly restrictive in robotics, where each data point must be physically executed in the real world. Consequently, there is a critical need for alternative data sources for robotics and frameworks that enable learning from such data. In this work, we present Point Policy, a new method for learning robot policies exclusively from offline human demonstration videos and without any teleoperation data. Point Policy leverages state-of-the-art vision models and policy architectures to translate human hand poses into robot poses while capturing object states through semantically meaningful key points. This approach yields a morphology-agnostic representation that facilitates effective policy learning. Our experiments on 8 real-world tasks demonstrate an overall 75% absolute improvement over prior works when evaluated in identical settings as training. Further, Point Policy exhibits a 74% gain across tasks for novel object instances and is robust to significant background clutter. Videos of the robot are best viewed at https://point-policy.github.io/.
title Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation
topic Robotics
url https://arxiv.org/abs/2502.20391