Compositional Diffusion-Based Continuous Constraint Solvers
This addresses robotic planning problems by enabling more efficient handling of continuous constraints, though it appears incremental as it builds on existing diffusion and factor graph methods.
The paper tackles solving continuous constraint satisfaction problems in robotic reasoning by introducing Diffusion-CCSP, which uses diffusion models on factor graphs to derive global solutions, achieving strong generalization to novel constraint combinations and integration into task and motion planning.
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/