Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement
This addresses the challenge of multi-modal rearrangement for robotics and AI applications, offering a method that handles many geometrically-similar solutions, though it is incremental in improving generalization and precision.
The authors tackled the problem of rearranging objects in a scene to achieve specific placing relationships, such as inserting a book into a bookshelf slot, by proposing a system that generalizes to novel geometries, poses, and layouts using 3D point clouds and an iterative pose de-noising training procedure, demonstrating it on three distinct tasks in simulation and real-world settings.
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/