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/

翻译：本文提出了一种用于在机器人推理与规划中学习求解连续约束满足问题（CCSP）的方法。以往方法主要依赖手工设计或针对特定约束类型的学习生成器，并在其他约束被违反时拒绝其赋值。与此不同，我们的模型——组合扩散连续约束求解器（Diffusion-CCSP）通过将CCSP表示为因子图，并组合针对各约束类型训练得到的扩散模型能量，从而导出全局解。Diffusion-CCSP在已知约束的新颖组合上展现出强大的泛化能力，并可集成至任务与运动规划器中，以制定包含离散和连续参数动作的长时域规划。项目网站：https://diffusion-ccsp.github.io/