ENCODE: a dEep poiNt Cloud ODometry nEtwork

Ego-motion estimation is a key requirement for the simultaneous localization and mapping (SLAM) problem. The traditional pipeline goes through feature extraction, feature matching and pose estimation, whose performance depends on the manually designed features. In this paper, we are motivated by the strong performance of deep learning methods in other computer vision and robotics tasks. We replace hand-crafted features with a neural network and directly estimate the relative pose between two adjacent scans from a LiDAR sensor using ENCODE: a dEep poiNt Cloud ODometry nEtwork. Firstly, a spherical projection of the input point cloud is performed to acquire a multi-channel vertex map. Then a multi-layer network backbone is applied to learn the abstracted features and a fully connected layer is adopted to estimate the 6-DoF ego-motion. Additionally, a map-to-map optimization module is applied to update the local poses and output a smooth map. Experiments on multiple datasets demonstrate that the proposed method achieves the best performance in comparison to state-of-the-art methods and is capable of providing accurate poses with low drift in various kinds of scenarios.

Authors

• Yihuan Zhang
• Liang Wang
• Chen Fu
• Yifan Dai
• John M. Dolan

Keywords

• Deep learning
• Simultaneous localization and mapping
• Laser radar
• Conferences
• Pose estimation
• Pipelines
• Neural networks
• Point Cloud
• Neural Network
• Handcrafted Features
• Backbone Network
• Feature Matching
• LiDAR Sensor
• Kind Of Scenario
• Input Point Cloud
• Spherical Projection
• Contralateral
• Computational Cost
• Convolutional Neural Network
• Deep Neural Network
• Mapping Method
• Inertial Measurement Unit
• Deep Learning-based Methods
• CNN-based Methods
• Iterative Closest Point
• Feature-based Methods
• Urban Scenarios
• Mapping Module
• Visual Odometry
• KITTI Dataset
• Geometry Constraints
• Point Cloud Data
• Point Cloud Registration
• Single Neural Network