Global Pose Estimation with an Attention-Based Recurrent Network

By Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov. 2018

73 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “Chaplot et al. (2018) introduce a network structure mimicking the Bayesian ﬁltering process with a specially designed perception model.”
Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review (2020, unknown): “2018 [149] Pose Estimation End-to-end trained model that consist of a local pose estimation model, pose selection module, and graph optimization process.”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, background): “Recently, a differentiable architecture named neural graph optimizer is proposed for global pose graph optimization [136].”
Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal (2018, methodology): “In the navigation domain, learning architectures have been proposed for creating explicit maps [11, 12], and agents have been trained to navigate without explicit maps using laser sensing [13, 14] and directly from images [15, 16, 17].”
Cross-View Policy Learning for Street Navigation (2019, background): “Subsequent work on Deep Reinforcement Learning focused on implicit goal-driven visual navigation [28, 7, 39, 46] and addressed generalization in unseen environments through implicit [33, 43] or explicit [47, 36] map representations.”