Global Pose Estimation with an Attention-Based Recurrent Network
| Autor: | Jian Zhang, Emilio Parisotto, Devendra Singh Chaplot, Ruslan Salakhutdinov |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Feature engineering 0209 industrial biotechnology Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Simultaneous localization and mapping Machine learning computer.software_genre Machine Learning (cs.LG) Computer Science - Robotics 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering Visual odometry Pose Artificial neural network business.industry Graph theory Computer Science - Learning Graph (abstract data type) 020201 artificial intelligence & image processing Artificial intelligence business Robotics (cs.RO) computer |
| Zdroj: | CVPR Workshops |
| DOI: | 10.1109/cvprw.2018.00061 |
| Popis: | 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. Comment: First two authors contributed equally |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|