FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation

TL;DR

FlowBotHD introduces a history-aware diffusion network that effectively handles visual ambiguities in manipulating articulated objects, improving stability and accuracy in uncertain scenarios like occlusions and symmetric features.

Contribution

The paper presents a novel history-aware diffusion approach that models multi-modal articulation modes and leverages observation history to resolve ambiguities in articulated object manipulation.

Findings

Achieves state-of-the-art performance on articulated object manipulation tasks.

Significantly improves handling of visual ambiguities and occlusions.

Demonstrates robustness in distinguishing articulation modes under challenging conditions.

Abstract

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/.