# LO-Net: Deep Real-time Lidar Odometry

## TL;DR

LO-Net is a deep learning pipeline for real-time lidar odometry that learns feature representations end-to-end and outperforms existing learning-based methods while matching state-of-the-art accuracy.

## Contribution

Introduces LO-Net, a novel end-to-end deep convolutional network for lidar odometry that incorporates a mask-weighted geometric loss and a scan-to-map module.

## Key findings

- LO-Net outperforms existing learning-based approaches.
- LO-Net achieves similar accuracy to LOAM, a state-of-the-art geometry-based method.
- The method effectively learns feature representations for odometry estimation.

## Abstract

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.