CNN for IMU assisted odometry estimation using velodyne LiDAR

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices for the training of proposed networks and for the prediction. Our networks show significantly better precision in the estimation of translational motion parameters comparing with state of the art method LOAM, while achieving real-time performance. Together with IMU support, high quality odometry estimation and LiDAR data registration is realized. Moreover, we propose alternative CNNs trained for the prediction of rotational motion parameters while achieving results also comparable with state of the art. The proposed method can replace wheel encoders in odometry estimation or supplement missing GPS data, when the GNSS signal absents (e.g. during the indoor mapping). Our solution brings real-time performance and precision which are useful to provide online preview of the mapping results and verification of the map completeness in real time.

I. Introduction

Recently, many solutions for indoor and outdoor 3D mapping using LiDAR sensors have been introduced, proving that the problem of odometry estimation and point cloud registration is relevant and solutions are demanded. The Leica¹

Http://leica-geosystems.com

company introduced Pegasus backpack equipped with multiple Velodyne LiDARs, RGB cameras, including IMU and GNSS sensors supporting the point cloud alignment. Geoslam²

Https://geoslam.com

uses simple range-finder accompanied with IMU unit in their hand-helded mapping ZEB products. Companies like LiDARUSA and RIEGL³

Https://www.lidarusa.com, http://www.riegl.com

build their LiDAR systems primarily targeting outdoor ground and aerial mapping. Such systems require readings from IMU and GNSS sensors in order to align captured point clouds. These requirements restrict the systems to be used for mapping the areas where GNSS is available.