Saved in:
Bibliographic Details
Main Authors: Wang, Jianren, Liu, Kangni, Guo, Dingkun, Zhou, Xian, Atkeson, Christopher G
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.12674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914954230104064
author Wang, Jianren
Liu, Kangni
Guo, Dingkun
Zhou, Xian
Atkeson, Christopher G
author_facet Wang, Jianren
Liu, Kangni
Guo, Dingkun
Zhou, Xian
Atkeson, Christopher G
contents Learning to manipulate dynamic and deformable objects from a single demonstration video holds great promise in terms of scalability. Previous approaches have predominantly focused on either replaying object relationships or actor trajectories. The former often struggles to generalize across diverse tasks, while the latter suffers from data inefficiency. Moreover, both methodologies encounter challenges in capturing invisible physical attributes, such as forces. In this paper, we propose to interpret video demonstrations through Parameterized Symbolic Abstraction Graphs (PSAG), where nodes represent objects and edges denote relationships between objects. We further ground geometric constraints through simulation to estimate non-geometric, visually imperceptible attributes. The augmented PSAG is then applied in real robot experiments. Our approach has been validated across a range of tasks, such as Cutting Avocado, Cutting Vegetable, Pouring Liquid, Rolling Dough, and Slicing Pizza. We demonstrate successful generalization to novel objects with distinct visual and physical properties.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12674
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs
Wang, Jianren
Liu, Kangni
Guo, Dingkun
Zhou, Xian
Atkeson, Christopher G
Robotics
Computer Vision and Pattern Recognition
Learning to manipulate dynamic and deformable objects from a single demonstration video holds great promise in terms of scalability. Previous approaches have predominantly focused on either replaying object relationships or actor trajectories. The former often struggles to generalize across diverse tasks, while the latter suffers from data inefficiency. Moreover, both methodologies encounter challenges in capturing invisible physical attributes, such as forces. In this paper, we propose to interpret video demonstrations through Parameterized Symbolic Abstraction Graphs (PSAG), where nodes represent objects and edges denote relationships between objects. We further ground geometric constraints through simulation to estimate non-geometric, visually imperceptible attributes. The augmented PSAG is then applied in real robot experiments. Our approach has been validated across a range of tasks, such as Cutting Avocado, Cutting Vegetable, Pouring Liquid, Rolling Dough, and Slicing Pizza. We demonstrate successful generalization to novel objects with distinct visual and physical properties.
title One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.12674