BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly

Yan Shen, Ruihai Wu, Yubin Ke, Xinyuan Song, Zeyi Li, Xiaoqi Li, Hongwei Fan, Haoran Lu, Hao Dong
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54559-54581, 2025.

Abstract

Shape assembly, the process of combining parts into a complete whole, is a crucial skill for robots with broad real-world applications. Among the various assembly tasks, geometric assembly—where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)—is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-shen25i, title = {{B}i{A}ssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly}, author = {Shen, Yan and Wu, Ruihai and Ke, Yubin and Song, Xinyuan and Li, Zeyi and Li, Xiaoqi and Fan, Hongwei and Lu, Haoran and Dong, Hao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {54559--54581}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/shen25i/shen25i.pdf}, url = {https://proceedings.mlr.press/v267/shen25i.html}, abstract = {Shape assembly, the process of combining parts into a complete whole, is a crucial skill for robots with broad real-world applications. Among the various assembly tasks, geometric assembly—where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)—is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods.} }
Endnote
%0 Conference Paper %T BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly %A Yan Shen %A Ruihai Wu %A Yubin Ke %A Xinyuan Song %A Zeyi Li %A Xiaoqi Li %A Hongwei Fan %A Haoran Lu %A Hao Dong %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-shen25i %I PMLR %P 54559--54581 %U https://proceedings.mlr.press/v267/shen25i.html %V 267 %X Shape assembly, the process of combining parts into a complete whole, is a crucial skill for robots with broad real-world applications. Among the various assembly tasks, geometric assembly—where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)—is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods.
APA
Shen, Y., Wu, R., Ke, Y., Song, X., Li, Z., Li, X., Fan, H., Lu, H. & Dong, H.. (2025). BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:54559-54581 Available from https://proceedings.mlr.press/v267/shen25i.html.

Related Material