Saved in:
Bibliographic Details
Main Authors: Li, Yishu, Leng, Wen Hui, Fang, Yiming, Eisner, Ben, Held, David
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07078
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929650927665152
author Li, Yishu
Leng, Wen Hui
Fang, Yiming
Eisner, Ben
Held, David
author_facet Li, Yishu
Leng, Wen Hui
Fang, Yiming
Eisner, Ben
Held, David
contents We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation modes: for instance, when the articulation direction (e.g. push, pull, slide) or location (e.g. left side, right side) of a fully closed door are uncertain, or when distinguishing features like the plane of the door are occluded due to the viewing angle. To tackle these challenges, we propose a history-aware diffusion network that can model multi-modal distributions over articulation modes for articulated objects; our method further uses observation history to distinguish between modes and make stable predictions under occlusions. Experiments and analysis demonstrate that our method achieves state-of-art performance on articulated object manipulation and dramatically improves performance for articulated objects containing visual ambiguities. Our project website is available at https://flowbothd.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07078
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation
Li, Yishu
Leng, Wen Hui
Fang, Yiming
Eisner, Ben
Held, David
Robotics
We introduce a novel approach for manipulating articulated objects which are visually ambiguous, such doors which are symmetric or which are heavily occluded. These ambiguities can cause uncertainty over different possible articulation modes: for instance, when the articulation direction (e.g. push, pull, slide) or location (e.g. left side, right side) of a fully closed door are uncertain, or when distinguishing features like the plane of the door are occluded due to the viewing angle. To tackle these challenges, we propose a history-aware diffusion network that can model multi-modal distributions over articulation modes for articulated objects; our method further uses observation history to distinguish between modes and make stable predictions under occlusions. Experiments and analysis demonstrate that our method achieves state-of-art performance on articulated object manipulation and dramatically improves performance for articulated objects containing visual ambiguities. Our project website is available at https://flowbothd.github.io/.
title FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation
topic Robotics
url https://arxiv.org/abs/2410.07078