Generative Factor Chaining: Coordinated Manipulation with Diffusion-based Factor Graph

Utkarsh Aashu Mishra, Yongxin Chen, Danfei Xu

Keywords: Task and Motion Planning, Manipulation Planning, Bimanual Manipulation, Generative Models

TL;DR: We present Generative Factor Chaining (GFC), a novel approach based on modularized generative models for learning and composing skills in complex tasks.

Abstract: Learning to plan for multi-step, multi-manipulator tasks is notoriously difficult because of the large search space and the complex constraint satisfaction problems. We present Generative Factor Chaining (GFC), a composable generative model for planning. GFC represents a planning problem as a spatial-temporal factor graph, where nodes represent objects and robots in the scene, spatial factors capture the distributions of valid relationships among nodes, and temporal factors represent the distributions of skill transitions. Each factor is implemented as a modular diffusion model, which are composed during inference to generate feasible long-horizon plans through bi-directional message passing. We show that GFC can solve complex bimanual manipulation tasks and exhibits strong generalization to unseen planning tasks with novel combinations of objects and constraints. More details can be found at: https://sites.google.com/view/generative-factor-chaining

Website: https://generative-fc.github.io/

Student Paper: yes

Submission Number: 282