Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement

Anthony Simeonov, Ankit Goyal, Lucas Manuelli, Yen-Chen Lin, Alina Sarmiento, Alberto Rodriguez Garcia, Pulkit Agrawal, Dieter Fox

Keywords: Object Rearrangement, Multi-modality, Manipulation, Point Clouds, Relations, Diffusion

TL;DR: A method for rearranging objects in scenes that present multi-modal placement locations via iterative pose de-noising on object-scene point clouds.

Abstract: We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal outputs while remaining precise and accurate. We also show the advantages of conditioning on relevant local geometric features while ignoring irrelevant global structure that harms both generalization and precision. We demonstrate our approach on three distinct rearrangement tasks that require handling multi-modality and generalization over object shape and pose in both simulation and the real world. Project website, code, and videos: https://anthonysimeonov.github.io/rpdiff-multi-modal

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://www.youtube.com/watch?v=x9noTl_aqu0&ab_channel=AnthonySimeonov

Website: https://anthonysimeonov.github.io/rpdiff-multi-modal/

Code: https://github.com/anthonysimeonov/rpdiff

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/shelving-stacking-hanging-relational-pose/code)