Compositional Diffusion-Based Continuous Constraint Solvers

被引：0

作者：

Yang, Zhutian ^{[1
]}

Mao, Jiayuan ^{[1
]}

Du, Yilun ^{[1
]}

Wu, Jiajun ^{[2
]}

Tenenbaum, Joshua B. ^{[1
]}

Lozano-Perez, Tomas ^{[1
]}

Kaelbling, Leslie Pack ^{[1
]}

机构：

[1] MIT, Cambridge, MA 02139 USA

[2] Stanford Univ, Stanford, CA USA

来源：

CONFERENCE ON ROBOT LEARNING, VOL 229 | 2023年 / 229卷

关键词：

Diffusion Models; Constraint Satisfaction Problems; Task and Motion Planning;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. Project site: https://diffusion- ccsp.github.io/

引用

页数：24