Compositional and Scalable Object SLAM

Download: PDF.

“Compositional and Scalable Object SLAM” by A. Sharma, W. Dong, and M. Kaess. In Proc. IEEE Intl. Conf. on Robotics and Automation, ICRA, (Xi'an, China), May 2021. To appear.

Abstract

We present a fast, scalable, and accurate Simultaneous Localization and Mapping (SLAM) system that represents indoor scenes as a graph of objects. Leveraging the observation that artificial environments are structured and occupied by recognizable objects, we show that a compositional and scalable object mapping formulation is amenable to a robust SLAM solution for drift-free large-scale indoor reconstruction. To achieve this, we propose a novel semantically assisted data association strategy that results in unambiguous persistent object landmarks and a 2.5D compositional rendering method that enables reliable frame-to-model RGB-D tracking. Consequently, we deliver an optimized online implementation that can run at near frame rate with a single graphics card, and provide a comprehensive evaluation against state-of-the-art baselines. An open-source implementation will be provided at https://github.com/rpl-cmu/object-slam.

Download: PDF.

BibTeX entry:

@inproceedings{Sharma21icra,
   author = {A. Sharma and W. Dong and M. Kaess},
   title = {Compositional and Scalable Object {SLAM}},
   booktitle = {Proc. IEEE Intl. Conf. on Robotics and Automation, ICRA},
   address = {Xi'an, China},
   month = may,
   year = {2021},
   note = {To appear}
}
Last updated: March 26, 2021