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

Yishu Li, Wen Hui Leng, Yiming Fang, Ben Eisner, David Held
Proceedings of The 8th Conference on Robot Learning, PMLR 270:5271-5293, 2025.

Abstract

We introduce a novel approach to manipulate articulated objects with ambiguities, such as opening a door, in which multi-modality and occlusions create ambiguities about the opening side and direction. Multi-modality occurs when the method to open a fully closed door (push, pull, slide) is uncertain, or the side from which it should be opened is uncertain. Occlusions further obscure the door’s shape from certain angles, creating further ambiguities during the occlusion. To tackle these challenges, we propose a history-aware diffusion network that models the multi-modal distribution of the articulated object and uses history to disambiguate actions and make stable predictions under occlusions. Experiments and analysis demonstrate the state-of-art performance of our method and specifically improvements in ambiguity-caused failure modes. Our project website is available at https://flowbothd.github.io/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-li25d, title = {FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation}, author = {Li, Yishu and Leng, Wen Hui and Fang, Yiming and Eisner, Ben and Held, David}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {5271--5293}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/li25d/li25d.pdf}, url = {https://proceedings.mlr.press/v270/li25d.html}, abstract = {We introduce a novel approach to manipulate articulated objects with ambiguities, such as opening a door, in which multi-modality and occlusions create ambiguities about the opening side and direction. Multi-modality occurs when the method to open a fully closed door (push, pull, slide) is uncertain, or the side from which it should be opened is uncertain. Occlusions further obscure the door’s shape from certain angles, creating further ambiguities during the occlusion. To tackle these challenges, we propose a history-aware diffusion network that models the multi-modal distribution of the articulated object and uses history to disambiguate actions and make stable predictions under occlusions. Experiments and analysis demonstrate the state-of-art performance of our method and specifically improvements in ambiguity-caused failure modes. Our project website is available at https://flowbothd.github.io/.} }
Endnote
%0 Conference Paper %T FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation %A Yishu Li %A Wen Hui Leng %A Yiming Fang %A Ben Eisner %A David Held %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-li25d %I PMLR %P 5271--5293 %U https://proceedings.mlr.press/v270/li25d.html %V 270 %X We introduce a novel approach to manipulate articulated objects with ambiguities, such as opening a door, in which multi-modality and occlusions create ambiguities about the opening side and direction. Multi-modality occurs when the method to open a fully closed door (push, pull, slide) is uncertain, or the side from which it should be opened is uncertain. Occlusions further obscure the door’s shape from certain angles, creating further ambiguities during the occlusion. To tackle these challenges, we propose a history-aware diffusion network that models the multi-modal distribution of the articulated object and uses history to disambiguate actions and make stable predictions under occlusions. Experiments and analysis demonstrate the state-of-art performance of our method and specifically improvements in ambiguity-caused failure modes. Our project website is available at https://flowbothd.github.io/.
APA
Li, Y., Leng, W.H., Fang, Y., Eisner, B. & Held, D.. (2025). FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:5271-5293 Available from https://proceedings.mlr.press/v270/li25d.html.

Related Material