Composable Part-Based Manipulation

TL;DR

This paper introduces CPM, a novel method that uses object-part decomposition and correspondences to enhance robotic manipulation learning and generalization across diverse objects and tasks.

Contribution

It presents a new composable diffusion model framework that captures inter-object part correspondences for improved manipulation skill generalization.

Findings

Effective in simulated environments

Robust performance in real-world scenarios

Enhanced generalization to novel objects

Abstract

In this paper, we propose composable part-based manipulation (CPM), a novel approach that leverages object-part decomposition and part-part correspondences to improve learning and generalization of robotic manipulation skills. By considering the functional correspondences between object parts, we conceptualize functional actions, such as pouring and constrained placing, as combinations of different correspondence constraints. CPM comprises a collection of composable diffusion models, where each model captures a different inter-object correspondence. These diffusion models can generate parameters for manipulation skills based on the specific object parts. Leveraging part-based correspondences coupled with the task decomposition into distinct constraints enables strong generalization to novel objects and object categories. We validate our approach in both simulated and real-world scenarios, demonstrating its effectiveness in achieving robust and generalized manipulation capabilities.