LO-Net: Deep Real-time Lidar Odometry
This work addresses real-time localization for autonomous vehicles or robotics, but it is incremental as it builds on existing learning-based approaches.
The authors tackled lidar odometry estimation by introducing LO-Net, a deep convolutional network trained end-to-end with a mask-weighted geometric constraint loss, achieving similar accuracy to the state-of-the-art geometry-based method LOAM on benchmark datasets.
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation. Unlike most existing lidar odometry (LO) estimations that go through individually designed feature selection, feature matching, and pose estimation pipeline, LO-Net can be trained in an end-to-end manner. With a new mask-weighted geometric constraint loss, LO-Net can effectively learn feature representation for LO estimation, and can implicitly exploit the sequential dependencies and dynamics in the data. We also design a scan-to-map module, which uses the geometric and semantic information learned in LO-Net, to improve the estimation accuracy. Experiments on benchmark datasets demonstrate that LO-Net outperforms existing learning based approaches and has similar accuracy with the state-of-the-art geometry-based approach, LOAM.