Compositional Diffusion-Based Continuous Constraint Solvers

Zhutian Yang, Jiayuan Mao, Yilun Du, Jiajun Wu, Joshua B. Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3242-3265, 2023.

Abstract

This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning. Previous methods primarily rely on hand-engineering or learning generators for specific constraint types and then rejecting the value assignments when other constraints are violated. By contrast, our model, the compositional diffusion continuous constraint solver (Diffusion-CCSP) derives global solutions to CCSPs by representing them as factor graphs and combining the energies of diffusion models trained to sample for individual constraint types. Diffusion-CCSP exhibits strong generalization to novel combinations of known constraints, and it can be integrated into a task and motion planner to devise long-horizon plans that include actions with both discrete and continuous parameters.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-yang23d, title = {Compositional Diffusion-Based Continuous Constraint Solvers}, author = {Yang, Zhutian and Mao, Jiayuan and Du, Yilun and Wu, Jiajun and Tenenbaum, Joshua B. and Lozano-P\'{e}rez, Tom\'{a}s and Kaelbling, Leslie Pack}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3242--3265}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/yang23d/yang23d.pdf}, url = {https://proceedings.mlr.press/v229/yang23d.html}, abstract = {This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning. Previous methods primarily rely on hand-engineering or learning generators for specific constraint types and then rejecting the value assignments when other constraints are violated. By contrast, our model, the compositional diffusion continuous constraint solver (Diffusion-CCSP) derives global solutions to CCSPs by representing them as factor graphs and combining the energies of diffusion models trained to sample for individual constraint types. Diffusion-CCSP exhibits strong generalization to novel combinations of known constraints, and it can be integrated into a task and motion planner to devise long-horizon plans that include actions with both discrete and continuous parameters.} }
Endnote
%0 Conference Paper %T Compositional Diffusion-Based Continuous Constraint Solvers %A Zhutian Yang %A Jiayuan Mao %A Yilun Du %A Jiajun Wu %A Joshua B. Tenenbaum %A Tomás Lozano-Pérez %A Leslie Pack Kaelbling %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-yang23d %I PMLR %P 3242--3265 %U https://proceedings.mlr.press/v229/yang23d.html %V 229 %X This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning. Previous methods primarily rely on hand-engineering or learning generators for specific constraint types and then rejecting the value assignments when other constraints are violated. By contrast, our model, the compositional diffusion continuous constraint solver (Diffusion-CCSP) derives global solutions to CCSPs by representing them as factor graphs and combining the energies of diffusion models trained to sample for individual constraint types. Diffusion-CCSP exhibits strong generalization to novel combinations of known constraints, and it can be integrated into a task and motion planner to devise long-horizon plans that include actions with both discrete and continuous parameters.
APA
Yang, Z., Mao, J., Du, Y., Wu, J., Tenenbaum, J.B., Lozano-Pérez, T. & Kaelbling, L.P.. (2023). Compositional Diffusion-Based Continuous Constraint Solvers. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3242-3265 Available from https://proceedings.mlr.press/v229/yang23d.html.

Related Material