NeuSE: Neural SE(3)-Equivariant Embedding for Consistent Spatial Understanding with Objects
Name
2303.07308.pdf
Size
11.6 MB
Format
Adobe PDF
Checksum (MD5)
cc83fef73cd15d5a1acf3fda717aae79
Author(s)
Fu, Jiahui
Du, Yilun
Singh, Kurran
Tenenbaum, Joshua
Leonard, John
Date Issued
July 10, 2023
Publisher
Robotics: Science and Systems Foundation
Citation
Fu, Jiahui, Du, Yilun, Singh, Kurran, Tenenbaum, Joshua and Leonard, John. 2023. "NeuSE: Neural SE(3)-Equivariant Embedding for Consistent Spatial Understanding with Objects."
Version
Author's final manuscript
Abstract
We present NeuSE, a novel Neural SE(3)-Equivariant Embedding for objects, and illustrate how it supports object SLAM for consistent spatial understanding with long-term scene changes. NeuSE is a set of latent object embeddings created from partial object observations. It serves as a compact point cloud surrogate for complete object models, encoding full shape information while transforming SE(3)-equivariantly in tandem with the object in the physical world. With NeuSE, relative frame transforms can be directly derived from inferred latent codes. Our proposed SLAM paradigm, using NeuSE for object shape and pose characterization, can operate independently or in conjunction with typical SLAM systems. It directly infers SE(3) camera pose constraints that are compatible with general SLAM pose graph optimization, while also maintaining a lightweight object-centric map that adapts to real-world changes. Our approach is evaluated on synthetic and real-world sequences featuring changed objects and shows improved localization accuracy and change-aware mapping capability, when working either standalone or jointly with a common SLAM pipeline.
Description
Robotics: Science and Systems Jul 10 – Jul 14, 2023 Daegu, Republic of Korea
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-ShareAlike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.15607/rss.2023.xix.068
