SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields

11/17/2022
by   Anthony Simeonov, et al.
0

We present a method for performing tasks involving spatial relations between novel object instances initialized in arbitrary poses directly from point cloud observations. Our framework provides a scalable way for specifying new tasks using only 5-10 demonstrations. Object rearrangement is formalized as the question of finding actions that configure task-relevant parts of the object in a desired alignment. This formalism is implemented in three steps: assigning a consistent local coordinate frame to the task-relevant object parts, determining the location and orientation of this coordinate frame on unseen object instances, and executing an action that brings these frames into the desired alignment. We overcome the key technical challenge of determining task-relevant local coordinate frames from a few demonstrations by developing an optimization method based on Neural Descriptor Fields (NDFs) and a single annotated 3D keypoint. An energy-based learning scheme to model the joint configuration of the objects that satisfies a desired relational task further improves performance. The method is tested on three multi-object rearrangement tasks in simulation and on a real robot. Project website, videos, and code: https://anthonysimeonov.github.io/r-ndf/

READ FULL TEXT

page 15

page 22

page 26

research
12/09/2021

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation

We present Neural Descriptor Fields (NDFs), an object representation tha...
research
02/07/2023

Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation

A robot operating in a household environment will see a wide range of un...
research
02/21/2023

Sim2Real^2: Actively Building Explicit Physics Model for Precise Articulated Object Manipulation

Accurately manipulating articulated objects is a challenging yet importa...
research
06/16/2022

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

End-to-end learning for visual robotic manipulation is known to suffer f...
research
07/10/2023

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

We propose a system for rearranging objects in a scene to achieve a desi...
research
12/08/2020

Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos

We address the task of aligning CAD models to a video sequence of a comp...
research
08/01/2022

Robust Change Detection Based on Neural Descriptor Fields

The ability to reason about changes in the environment is crucial for ro...

Please sign up or login with your details

Forgot password? Click here to reset