Global Pose Estimation With an Attention-Based Recurrent Network

Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 237-246

Abstract


The ability for an agent to localize itself within an environment is crucial for many real-world applications. For unknown environments, Simultaneous Localization and Mapping (SLAM) enables incremental and concurrent building of and localizing within a map. We present a new, differentiable architecture, Neural Graph Optimizer, progressing towards a complete neural network solution for SLAM by designing a system composed of a local pose estimation model, a novel pose selection module, and a novel graph optimization process. The entire architecture is trained in an end-to-end fashion, enabling the network to automatically learn domain-specific features relevant to the visual odometry and avoid the involved process of feature engineering. We demonstrate the effectiveness of our system on a simulated 2D maze and the 3D ViZ-Doom environment.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Parisotto_2018_CVPR_Workshops,
author = {Parisotto, Emilio and Singh Chaplot, Devendra and Zhang, Jian and Salakhutdinov, Ruslan},
title = {Global Pose Estimation With an Attention-Based Recurrent Network},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}